
# Import libraries 
import numpy as np
import pandas as pd
import missingno as msno
import matplotlib.pyplot as plt
import seaborn as sns

from sklearn import linear_model, metrics
from sklearn.linear_model import LinearRegression, Ridge, Lasso
from sklearn.preprocessing import PolynomialFeatures, MinMaxScaler
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import mean_squared_error, r2_score

import os

#to ignore Warnings
import warnings
warnings.filterwarnings('ignore')


#Reading the data
Data_train = pd.read_csv("train.csv")


Data_train.head()


Data_train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1460 entries, 0 to 1459
Data columns (total 81 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   Id             1460 non-null   int64  
 1   MSSubClass     1460 non-null   int64  
 2   MSZoning       1460 non-null   object 
 3   LotFrontage    1201 non-null   float64
 4   LotArea        1460 non-null   int64  
 5   Street         1460 non-null   object 
 6   Alley          91 non-null     object 
 7   LotShape       1460 non-null   object 
 8   LandContour    1460 non-null   object 
 9   Utilities      1460 non-null   object 
 10  LotConfig      1460 non-null   object 
 11  LandSlope      1460 non-null   object 
 12  Neighborhood   1460 non-null   object 
 13  Condition1     1460 non-null   object 
 14  Condition2     1460 non-null   object 
 15  BldgType       1460 non-null   object 
 16  HouseStyle     1460 non-null   object 
 17  OverallQual    1460 non-null   int64  
 18  OverallCond    1460 non-null   int64  
 19  YearBuilt      1460 non-null   int64  
 20  YearRemodAdd   1460 non-null   int64  
 21  RoofStyle      1460 non-null   object 
 22  RoofMatl       1460 non-null   object 
 23  Exterior1st    1460 non-null   object 
 24  Exterior2nd    1460 non-null   object 
 25  MasVnrType     1452 non-null   object 
 26  MasVnrArea     1452 non-null   float64
 27  ExterQual      1460 non-null   object 
 28  ExterCond      1460 non-null   object 
 29  Foundation     1460 non-null   object 
 30  BsmtQual       1423 non-null   object 
 31  BsmtCond       1423 non-null   object 
 32  BsmtExposure   1422 non-null   object 
 33  BsmtFinType1   1423 non-null   object 
 34  BsmtFinSF1     1460 non-null   int64  
 35  BsmtFinType2   1422 non-null   object 
 36  BsmtFinSF2     1460 non-null   int64  
 37  BsmtUnfSF      1460 non-null   int64  
 38  TotalBsmtSF    1460 non-null   int64  
 39  Heating        1460 non-null   object 
 40  HeatingQC      1460 non-null   object 
 41  CentralAir     1460 non-null   object 
 42  Electrical     1459 non-null   object 
 43  1stFlrSF       1460 non-null   int64  
 44  2ndFlrSF       1460 non-null   int64  
 45  LowQualFinSF   1460 non-null   int64  
 46  GrLivArea      1460 non-null   int64  
 47  BsmtFullBath   1460 non-null   int64  
 48  BsmtHalfBath   1460 non-null   int64  
 49  FullBath       1460 non-null   int64  
 50  HalfBath       1460 non-null   int64  
 51  BedroomAbvGr   1460 non-null   int64  
 52  KitchenAbvGr   1460 non-null   int64  
 53  KitchenQual    1460 non-null   object 
 54  TotRmsAbvGrd   1460 non-null   int64  
 55  Functional     1460 non-null   object 
 56  Fireplaces     1460 non-null   int64  
 57  FireplaceQu    770 non-null    object 
 58  GarageType     1379 non-null   object 
 59  GarageYrBlt    1379 non-null   float64
 60  GarageFinish   1379 non-null   object 
 61  GarageCars     1460 non-null   int64  
 62  GarageArea     1460 non-null   int64  
 63  GarageQual     1379 non-null   object 
 64  GarageCond     1379 non-null   object 
 65  PavedDrive     1460 non-null   object 
 66  WoodDeckSF     1460 non-null   int64  
 67  OpenPorchSF    1460 non-null   int64  
 68  EnclosedPorch  1460 non-null   int64  
 69  3SsnPorch      1460 non-null   int64  
 70  ScreenPorch    1460 non-null   int64  
 71  PoolArea       1460 non-null   int64  
 72  PoolQC         7 non-null      object 
 73  Fence          281 non-null    object 
 74  MiscFeature    54 non-null     object 
 75  MiscVal        1460 non-null   int64  
 76  MoSold         1460 non-null   int64  
 77  YrSold         1460 non-null   int64  
 78  SaleType       1460 non-null   object 
 79  SaleCondition  1460 non-null   object 
 80  SalePrice      1460 non-null   int64  
dtypes: float64(3), int64(35), object(43)
memory usage: 924.0+ KB


Data_train.describe()


cor = Data_train.corr()
cor


#plotting correlation heatmap
plt.figure(figsize=(50,20))
sns.heatmap(cor, cmap="YlGnBu", annot = True)

plt.show()


msno.bar(Data_train)

<Axes: >


# Drop columns with high missing values
col_to_drop = ['Id','Alley','PoolQC','Fence','MiscFeature']
Data_train = Data_train.drop(col_to_drop, axis = 1)
Data_train.shape

(1460, 76)


col_zero_count = Data_train.eq(0).sum(axis=0)


col_zero_count[col_zero_count > 1000]

BsmtFinSF2       1293
LowQualFinSF     1434
BsmtHalfBath     1378
EnclosedPorch    1252
3SsnPorch        1436
ScreenPorch      1344
PoolArea         1453
MiscVal          1408
dtype: int64


Data_train.hist(bins=50,figsize=(20,15))

array([[<Axes: title={'center': 'MSSubClass'}>,
        <Axes: title={'center': 'LotFrontage'}>,
        <Axes: title={'center': 'LotArea'}>,
        <Axes: title={'center': 'OverallQual'}>,
        <Axes: title={'center': 'OverallCond'}>,
        <Axes: title={'center': 'YearBuilt'}>],
       [<Axes: title={'center': 'YearRemodAdd'}>,
        <Axes: title={'center': 'MasVnrArea'}>,
        <Axes: title={'center': 'BsmtFinSF1'}>,
        <Axes: title={'center': 'BsmtFinSF2'}>,
        <Axes: title={'center': 'BsmtUnfSF'}>,
        <Axes: title={'center': 'TotalBsmtSF'}>],
       [<Axes: title={'center': '1stFlrSF'}>,
        <Axes: title={'center': '2ndFlrSF'}>,
        <Axes: title={'center': 'LowQualFinSF'}>,
        <Axes: title={'center': 'GrLivArea'}>,
        <Axes: title={'center': 'BsmtFullBath'}>,
        <Axes: title={'center': 'BsmtHalfBath'}>],
       [<Axes: title={'center': 'FullBath'}>,
        <Axes: title={'center': 'HalfBath'}>,
        <Axes: title={'center': 'BedroomAbvGr'}>,
        <Axes: title={'center': 'KitchenAbvGr'}>,
        <Axes: title={'center': 'TotRmsAbvGrd'}>,
        <Axes: title={'center': 'Fireplaces'}>],
       [<Axes: title={'center': 'GarageYrBlt'}>,
        <Axes: title={'center': 'GarageCars'}>,
        <Axes: title={'center': 'GarageArea'}>,
        <Axes: title={'center': 'WoodDeckSF'}>,
        <Axes: title={'center': 'OpenPorchSF'}>,
        <Axes: title={'center': 'EnclosedPorch'}>],
       [<Axes: title={'center': '3SsnPorch'}>,
        <Axes: title={'center': 'ScreenPorch'}>,
        <Axes: title={'center': 'PoolArea'}>,
        <Axes: title={'center': 'MiscVal'}>,
        <Axes: title={'center': 'MoSold'}>,
        <Axes: title={'center': 'YrSold'}>],
       [<Axes: title={'center': 'SalePrice'}>, <Axes: >, <Axes: >,
        <Axes: >, <Axes: >, <Axes: >]], dtype=object)


Col_to_del = col_zero_count[col_zero_count > 1168]
#Data_train[Col_to_del].hist(bins=50,figsize=(20,15))


Col_to_drop_list = ['BsmtFinSF2','LowQualFinSF','BsmtHalfBath','EnclosedPorch','3SsnPorch','ScreenPorch','PoolArea','MiscVal']


Data_train[Col_to_drop_list].hist(bins=50,figsize=(20,15))

array([[<Axes: title={'center': 'BsmtFinSF2'}>,
        <Axes: title={'center': 'LowQualFinSF'}>,
        <Axes: title={'center': 'BsmtHalfBath'}>],
       [<Axes: title={'center': 'EnclosedPorch'}>,
        <Axes: title={'center': '3SsnPorch'}>,
        <Axes: title={'center': 'ScreenPorch'}>],
       [<Axes: title={'center': 'PoolArea'}>,
        <Axes: title={'center': 'MiscVal'}>, <Axes: >]], dtype=object)


#Drop columns where most of the values are zero
Data_train = Data_train.drop(Col_to_drop_list, axis = 1)
Data_train.shape

(1460, 68)


cor = Data_train.corr()
#plotting correlation heatmap
plt.figure(figsize=(50,20))
sns.heatmap(cor, cmap="YlGnBu", annot = True)

plt.show()


cor["SalePrice"].sort_values(ascending=False)

SalePrice       1.000000
OverallQual     0.790982
GrLivArea       0.708624
GarageCars      0.640409
GarageArea      0.623431
TotalBsmtSF     0.613581
1stFlrSF        0.605852
FullBath        0.560664
TotRmsAbvGrd    0.533723
YearBuilt       0.522897
YearRemodAdd    0.507101
GarageYrBlt     0.486362
MasVnrArea      0.477493
Fireplaces      0.466929
BsmtFinSF1      0.386420
LotFrontage     0.351799
WoodDeckSF      0.324413
2ndFlrSF        0.319334
OpenPorchSF     0.315856
HalfBath        0.284108
LotArea         0.263843
BsmtFullBath    0.227122
BsmtUnfSF       0.214479
BedroomAbvGr    0.168213
MoSold          0.046432
YrSold         -0.028923
OverallCond    -0.077856
MSSubClass     -0.084284
KitchenAbvGr   -0.135907
Name: SalePrice, dtype: float64


#pair plot with OverallQual (categorical variable) and saleprice
plt.figure(figsize = [6,6])
plt.scatter(Data_train.SalePrice,Data_train.OverallQual)
plt.show()


#pair plot with GrLivArea and saleprice
plt.figure(figsize = [6,6])
plt.scatter(Data_train.SalePrice,Data_train.GrLivArea)
plt.show()


Data_train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1460 entries, 0 to 1459
Data columns (total 68 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   MSSubClass     1460 non-null   int64  
 1   MSZoning       1460 non-null   object 
 2   LotFrontage    1201 non-null   float64
 3   LotArea        1460 non-null   int64  
 4   Street         1460 non-null   object 
 5   LotShape       1460 non-null   object 
 6   LandContour    1460 non-null   object 
 7   Utilities      1460 non-null   object 
 8   LotConfig      1460 non-null   object 
 9   LandSlope      1460 non-null   object 
 10  Neighborhood   1460 non-null   object 
 11  Condition1     1460 non-null   object 
 12  Condition2     1460 non-null   object 
 13  BldgType       1460 non-null   object 
 14  HouseStyle     1460 non-null   object 
 15  OverallQual    1460 non-null   int64  
 16  OverallCond    1460 non-null   int64  
 17  YearBuilt      1460 non-null   int64  
 18  YearRemodAdd   1460 non-null   int64  
 19  RoofStyle      1460 non-null   object 
 20  RoofMatl       1460 non-null   object 
 21  Exterior1st    1460 non-null   object 
 22  Exterior2nd    1460 non-null   object 
 23  MasVnrType     1452 non-null   object 
 24  MasVnrArea     1452 non-null   float64
 25  ExterQual      1460 non-null   object 
 26  ExterCond      1460 non-null   object 
 27  Foundation     1460 non-null   object 
 28  BsmtQual       1423 non-null   object 
 29  BsmtCond       1423 non-null   object 
 30  BsmtExposure   1422 non-null   object 
 31  BsmtFinType1   1423 non-null   object 
 32  BsmtFinSF1     1460 non-null   int64  
 33  BsmtFinType2   1422 non-null   object 
 34  BsmtUnfSF      1460 non-null   int64  
 35  TotalBsmtSF    1460 non-null   int64  
 36  Heating        1460 non-null   object 
 37  HeatingQC      1460 non-null   object 
 38  CentralAir     1460 non-null   object 
 39  Electrical     1459 non-null   object 
 40  1stFlrSF       1460 non-null   int64  
 41  2ndFlrSF       1460 non-null   int64  
 42  GrLivArea      1460 non-null   int64  
 43  BsmtFullBath   1460 non-null   int64  
 44  FullBath       1460 non-null   int64  
 45  HalfBath       1460 non-null   int64  
 46  BedroomAbvGr   1460 non-null   int64  
 47  KitchenAbvGr   1460 non-null   int64  
 48  KitchenQual    1460 non-null   object 
 49  TotRmsAbvGrd   1460 non-null   int64  
 50  Functional     1460 non-null   object 
 51  Fireplaces     1460 non-null   int64  
 52  FireplaceQu    770 non-null    object 
 53  GarageType     1379 non-null   object 
 54  GarageYrBlt    1379 non-null   float64
 55  GarageFinish   1379 non-null   object 
 56  GarageCars     1460 non-null   int64  
 57  GarageArea     1460 non-null   int64  
 58  GarageQual     1379 non-null   object 
 59  GarageCond     1379 non-null   object 
 60  PavedDrive     1460 non-null   object 
 61  WoodDeckSF     1460 non-null   int64  
 62  OpenPorchSF    1460 non-null   int64  
 63  MoSold         1460 non-null   int64  
 64  YrSold         1460 non-null   int64  
 65  SaleType       1460 non-null   object 
 66  SaleCondition  1460 non-null   object 
 67  SalePrice      1460 non-null   int64  
dtypes: float64(3), int64(26), object(39)
memory usage: 775.8+ KB


### Handling Year features
#YearBuilt      1460 non-null   int64  
#YearRemodAdd   1460 non-null   int64  
#YrSold         1460 non-null   int64
#GarageYrBlt    1379 non-null   float64


Data_train['age'] = Data_train['YrSold']-Data_train['YearBuilt']
Data_train['age'].describe()

count    1460.000000
mean       36.547945
std        30.250152
min         0.000000
25%         8.000000
50%        35.000000
75%        54.000000
max       136.000000
Name: age, dtype: float64


Data_train['age_Remod'] = Data_train['YrSold']-Data_train['YearRemodAdd']
Data_train['age_Remod'].describe()

count    1460.000000
mean       22.950000
std        20.640653
min        -1.000000
25%         4.000000
50%        14.000000
75%        41.000000
max        60.000000
Name: age_Remod, dtype: float64


Data_train['GarageYrBlt'].fillna(0.0,inplace=True)
Data_train['age_Garage'] = Data_train['YrSold']-Data_train['GarageYrBlt']
Data_train['age_Garage'].describe()

count    1460.000000
mean      139.076027
std       453.714026
min         0.000000
25%         7.000000
50%        30.000000
75%        50.000000
max      2010.000000
Name: age_Garage, dtype: float64


#delete the year columns
Col_to_drop_list = ['YearBuilt','YearRemodAdd','YrSold','GarageYrBlt']
Data_train = Data_train.drop(Col_to_drop_list, axis = 1)
Data_train.shape

(1460, 67)


cor = Data_train.corr()
#plotting correlation heatmap
plt.figure(figsize=(50,20))
sns.heatmap(cor, cmap="YlGnBu", annot = True)

plt.show()


Data_train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1460 entries, 0 to 1459
Data columns (total 67 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   MSSubClass     1460 non-null   int64  
 1   MSZoning       1460 non-null   object 
 2   LotFrontage    1201 non-null   float64
 3   LotArea        1460 non-null   int64  
 4   Street         1460 non-null   object 
 5   LotShape       1460 non-null   object 
 6   LandContour    1460 non-null   object 
 7   Utilities      1460 non-null   object 
 8   LotConfig      1460 non-null   object 
 9   LandSlope      1460 non-null   object 
 10  Neighborhood   1460 non-null   object 
 11  Condition1     1460 non-null   object 
 12  Condition2     1460 non-null   object 
 13  BldgType       1460 non-null   object 
 14  HouseStyle     1460 non-null   object 
 15  OverallQual    1460 non-null   int64  
 16  OverallCond    1460 non-null   int64  
 17  RoofStyle      1460 non-null   object 
 18  RoofMatl       1460 non-null   object 
 19  Exterior1st    1460 non-null   object 
 20  Exterior2nd    1460 non-null   object 
 21  MasVnrType     1452 non-null   object 
 22  MasVnrArea     1452 non-null   float64
 23  ExterQual      1460 non-null   object 
 24  ExterCond      1460 non-null   object 
 25  Foundation     1460 non-null   object 
 26  BsmtQual       1423 non-null   object 
 27  BsmtCond       1423 non-null   object 
 28  BsmtExposure   1422 non-null   object 
 29  BsmtFinType1   1423 non-null   object 
 30  BsmtFinSF1     1460 non-null   int64  
 31  BsmtFinType2   1422 non-null   object 
 32  BsmtUnfSF      1460 non-null   int64  
 33  TotalBsmtSF    1460 non-null   int64  
 34  Heating        1460 non-null   object 
 35  HeatingQC      1460 non-null   object 
 36  CentralAir     1460 non-null   object 
 37  Electrical     1459 non-null   object 
 38  1stFlrSF       1460 non-null   int64  
 39  2ndFlrSF       1460 non-null   int64  
 40  GrLivArea      1460 non-null   int64  
 41  BsmtFullBath   1460 non-null   int64  
 42  FullBath       1460 non-null   int64  
 43  HalfBath       1460 non-null   int64  
 44  BedroomAbvGr   1460 non-null   int64  
 45  KitchenAbvGr   1460 non-null   int64  
 46  KitchenQual    1460 non-null   object 
 47  TotRmsAbvGrd   1460 non-null   int64  
 48  Functional     1460 non-null   object 
 49  Fireplaces     1460 non-null   int64  
 50  FireplaceQu    770 non-null    object 
 51  GarageType     1379 non-null   object 
 52  GarageFinish   1379 non-null   object 
 53  GarageCars     1460 non-null   int64  
 54  GarageArea     1460 non-null   int64  
 55  GarageQual     1379 non-null   object 
 56  GarageCond     1379 non-null   object 
 57  PavedDrive     1460 non-null   object 
 58  WoodDeckSF     1460 non-null   int64  
 59  OpenPorchSF    1460 non-null   int64  
 60  MoSold         1460 non-null   int64  
 61  SaleType       1460 non-null   object 
 62  SaleCondition  1460 non-null   object 
 63  SalePrice      1460 non-null   int64  
 64  age            1460 non-null   int64  
 65  age_Remod      1460 non-null   int64  
 66  age_Garage     1460 non-null   float64
dtypes: float64(3), int64(25), object(39)
memory usage: 764.3+ KB


# Handle all the rest of missing values with me value for numeric variables
Data_train.fillna(Data_train.median(),inplace=True)


Data_train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1460 entries, 0 to 1459
Data columns (total 67 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   MSSubClass     1460 non-null   int64  
 1   MSZoning       1460 non-null   object 
 2   LotFrontage    1460 non-null   float64
 3   LotArea        1460 non-null   int64  
 4   Street         1460 non-null   object 
 5   LotShape       1460 non-null   object 
 6   LandContour    1460 non-null   object 
 7   Utilities      1460 non-null   object 
 8   LotConfig      1460 non-null   object 
 9   LandSlope      1460 non-null   object 
 10  Neighborhood   1460 non-null   object 
 11  Condition1     1460 non-null   object 
 12  Condition2     1460 non-null   object 
 13  BldgType       1460 non-null   object 
 14  HouseStyle     1460 non-null   object 
 15  OverallQual    1460 non-null   int64  
 16  OverallCond    1460 non-null   int64  
 17  RoofStyle      1460 non-null   object 
 18  RoofMatl       1460 non-null   object 
 19  Exterior1st    1460 non-null   object 
 20  Exterior2nd    1460 non-null   object 
 21  MasVnrType     1452 non-null   object 
 22  MasVnrArea     1460 non-null   float64
 23  ExterQual      1460 non-null   object 
 24  ExterCond      1460 non-null   object 
 25  Foundation     1460 non-null   object 
 26  BsmtQual       1423 non-null   object 
 27  BsmtCond       1423 non-null   object 
 28  BsmtExposure   1422 non-null   object 
 29  BsmtFinType1   1423 non-null   object 
 30  BsmtFinSF1     1460 non-null   int64  
 31  BsmtFinType2   1422 non-null   object 
 32  BsmtUnfSF      1460 non-null   int64  
 33  TotalBsmtSF    1460 non-null   int64  
 34  Heating        1460 non-null   object 
 35  HeatingQC      1460 non-null   object 
 36  CentralAir     1460 non-null   object 
 37  Electrical     1459 non-null   object 
 38  1stFlrSF       1460 non-null   int64  
 39  2ndFlrSF       1460 non-null   int64  
 40  GrLivArea      1460 non-null   int64  
 41  BsmtFullBath   1460 non-null   int64  
 42  FullBath       1460 non-null   int64  
 43  HalfBath       1460 non-null   int64  
 44  BedroomAbvGr   1460 non-null   int64  
 45  KitchenAbvGr   1460 non-null   int64  
 46  KitchenQual    1460 non-null   object 
 47  TotRmsAbvGrd   1460 non-null   int64  
 48  Functional     1460 non-null   object 
 49  Fireplaces     1460 non-null   int64  
 50  FireplaceQu    770 non-null    object 
 51  GarageType     1379 non-null   object 
 52  GarageFinish   1379 non-null   object 
 53  GarageCars     1460 non-null   int64  
 54  GarageArea     1460 non-null   int64  
 55  GarageQual     1379 non-null   object 
 56  GarageCond     1379 non-null   object 
 57  PavedDrive     1460 non-null   object 
 58  WoodDeckSF     1460 non-null   int64  
 59  OpenPorchSF    1460 non-null   int64  
 60  MoSold         1460 non-null   int64  
 61  SaleType       1460 non-null   object 
 62  SaleCondition  1460 non-null   object 
 63  SalePrice      1460 non-null   int64  
 64  age            1460 non-null   int64  
 65  age_Remod      1460 non-null   int64  
 66  age_Garage     1460 non-null   float64
dtypes: float64(3), int64(25), object(39)
memory usage: 764.3+ KB


# Categorical variables
# Handle all the rest of missing values with NO as NA (not avaialable) is used if that feature not exist (eg. NA	No Basement data dictonary)
Data_train.fillna('NO',inplace=True)


Data_train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1460 entries, 0 to 1459
Data columns (total 67 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   MSSubClass     1460 non-null   int64  
 1   MSZoning       1460 non-null   object 
 2   LotFrontage    1460 non-null   float64
 3   LotArea        1460 non-null   int64  
 4   Street         1460 non-null   object 
 5   LotShape       1460 non-null   object 
 6   LandContour    1460 non-null   object 
 7   Utilities      1460 non-null   object 
 8   LotConfig      1460 non-null   object 
 9   LandSlope      1460 non-null   object 
 10  Neighborhood   1460 non-null   object 
 11  Condition1     1460 non-null   object 
 12  Condition2     1460 non-null   object 
 13  BldgType       1460 non-null   object 
 14  HouseStyle     1460 non-null   object 
 15  OverallQual    1460 non-null   int64  
 16  OverallCond    1460 non-null   int64  
 17  RoofStyle      1460 non-null   object 
 18  RoofMatl       1460 non-null   object 
 19  Exterior1st    1460 non-null   object 
 20  Exterior2nd    1460 non-null   object 
 21  MasVnrType     1460 non-null   object 
 22  MasVnrArea     1460 non-null   float64
 23  ExterQual      1460 non-null   object 
 24  ExterCond      1460 non-null   object 
 25  Foundation     1460 non-null   object 
 26  BsmtQual       1460 non-null   object 
 27  BsmtCond       1460 non-null   object 
 28  BsmtExposure   1460 non-null   object 
 29  BsmtFinType1   1460 non-null   object 
 30  BsmtFinSF1     1460 non-null   int64  
 31  BsmtFinType2   1460 non-null   object 
 32  BsmtUnfSF      1460 non-null   int64  
 33  TotalBsmtSF    1460 non-null   int64  
 34  Heating        1460 non-null   object 
 35  HeatingQC      1460 non-null   object 
 36  CentralAir     1460 non-null   object 
 37  Electrical     1460 non-null   object 
 38  1stFlrSF       1460 non-null   int64  
 39  2ndFlrSF       1460 non-null   int64  
 40  GrLivArea      1460 non-null   int64  
 41  BsmtFullBath   1460 non-null   int64  
 42  FullBath       1460 non-null   int64  
 43  HalfBath       1460 non-null   int64  
 44  BedroomAbvGr   1460 non-null   int64  
 45  KitchenAbvGr   1460 non-null   int64  
 46  KitchenQual    1460 non-null   object 
 47  TotRmsAbvGrd   1460 non-null   int64  
 48  Functional     1460 non-null   object 
 49  Fireplaces     1460 non-null   int64  
 50  FireplaceQu    1460 non-null   object 
 51  GarageType     1460 non-null   object 
 52  GarageFinish   1460 non-null   object 
 53  GarageCars     1460 non-null   int64  
 54  GarageArea     1460 non-null   int64  
 55  GarageQual     1460 non-null   object 
 56  GarageCond     1460 non-null   object 
 57  PavedDrive     1460 non-null   object 
 58  WoodDeckSF     1460 non-null   int64  
 59  OpenPorchSF    1460 non-null   int64  
 60  MoSold         1460 non-null   int64  
 61  SaleType       1460 non-null   object 
 62  SaleCondition  1460 non-null   object 
 63  SalePrice      1460 non-null   int64  
 64  age            1460 non-null   int64  
 65  age_Remod      1460 non-null   int64  
 66  age_Garage     1460 non-null   float64
dtypes: float64(3), int64(25), object(39)
memory usage: 764.3+ KB


#list of cat variables converted to dummy variables
cat_col_list = []
#list of features need to be deleted which has one value more than 80%
col_del_list = []


Data_train['MSSubClass'].astype('category').value_counts()

20     536
60     299
50     144
120     87
30      69
160     63
70      60
80      58
90      52
190     30
85      20
75      16
45      12
180     10
40       4
Name: MSSubClass, dtype: int64


MSSubClass = pd.get_dummies(Data_train.MSSubClass,drop_first=True)
MSSubClass = MSSubClass.add_prefix("MSSubClass_")
cat_col_list.append('MSSubClass')
MSSubClass


Data_train['MSZoning'].astype('category').value_counts()

RL         1151
RM          218
FV           65
RH           16
C (all)      10
Name: MSZoning, dtype: int64


MSZoning = pd.get_dummies(Data_train.MSZoning,drop_first=True)
MSZoning = MSZoning.add_prefix("MSZoning_")
cat_col_list.append('MSZoning')


Data_train['Street'].astype('category').value_counts()

Pave    1454
Grvl       6
Name: Street, dtype: int64


col_del_list.append('Street')


Data_train['LotShape'].astype('category').value_counts()

Reg    925
IR1    484
IR2     41
IR3     10
Name: LotShape, dtype: int64


LotShape = pd.get_dummies(Data_train.LotShape,drop_first=True)
LotShape = LotShape.add_prefix("LotShape_")
cat_col_list.append('LotShape')


Data_train['LandContour'].astype('category').value_counts()

Lvl    1311
Bnk      63
HLS      50
Low      36
Name: LandContour, dtype: int64


col_del_list.append('LandContour')


Data_train['Utilities'].astype('category').value_counts()

AllPub    1459
NoSeWa       1
Name: Utilities, dtype: int64


col_del_list.append('Utilities')


Data_train['LotConfig'].astype('category').value_counts()

Inside     1052
Corner      263
CulDSac      94
FR2          47
FR3           4
Name: LotConfig, dtype: int64


LotConfig = pd.get_dummies(Data_train.LotConfig,drop_first=True)
LotConfig = LotConfig.add_prefix("LotConfig_")
cat_col_list.append('LotConfig')


Data_train['LandSlope'].astype('category').value_counts()

Gtl    1382
Mod      65
Sev      13
Name: LandSlope, dtype: int64


col_del_list.append('LandSlope')


Data_train['Neighborhood'].astype('category').value_counts()

NAmes      225
CollgCr    150
OldTown    113
Edwards    100
Somerst     86
Gilbert     79
NridgHt     77
Sawyer      74
NWAmes      73
SawyerW     59
BrkSide     58
Crawfor     51
Mitchel     49
NoRidge     41
Timber      38
IDOTRR      37
ClearCr     28
StoneBr     25
SWISU       25
Blmngtn     17
MeadowV     17
BrDale      16
Veenker     11
NPkVill      9
Blueste      2
Name: Neighborhood, dtype: int64


Neighborhood = pd.get_dummies(Data_train.Neighborhood,drop_first=True)
Neighborhood = Neighborhood.add_prefix("Neighborhood_")
cat_col_list.append('Neighborhood')


Data_train['Condition1'].astype('category').value_counts()

Norm      1260
Feedr       81
Artery      48
RRAn        26
PosN        19
RRAe        11
PosA         8
RRNn         5
RRNe         2
Name: Condition1, dtype: int64


col_del_list.append('Condition1')


Data_train['Condition2'].astype('category').value_counts()

Norm      1445
Feedr        6
Artery       2
PosN         2
RRNn         2
PosA         1
RRAe         1
RRAn         1
Name: Condition2, dtype: int64


col_del_list.append('Condition2')


Data_train['BldgType'].astype('category').value_counts()

1Fam      1220
TwnhsE     114
Duplex      52
Twnhs       43
2fmCon      31
Name: BldgType, dtype: int64


col_del_list.append('BldgType')


Data_train['HouseStyle'].astype('category').value_counts()

1Story    726
2Story    445
1.5Fin    154
SLvl       65
SFoyer     37
1.5Unf     14
2.5Unf     11
2.5Fin      8
Name: HouseStyle, dtype: int64


HouseStyle = pd.get_dummies(Data_train.HouseStyle,drop_first=True)
HouseStyle = HouseStyle.add_prefix("HouseStyle_")
cat_col_list.append('HouseStyle')


Data_train['RoofStyle'].astype('category').value_counts()

Gable      1141
Hip         286
Flat         13
Gambrel      11
Mansard       7
Shed          2
Name: RoofStyle, dtype: int64


RoofStyle = pd.get_dummies(Data_train.RoofStyle,drop_first=True)
RoofStyle = RoofStyle.add_prefix("RoofStyle_")
cat_col_list.append('RoofStyle')


Data_train['RoofMatl'].astype('category').value_counts()

CompShg    1434
Tar&Grv      11
WdShngl       6
WdShake       5
ClyTile       1
Membran       1
Metal         1
Roll          1
Name: RoofMatl, dtype: int64


# Add to del list
col_del_list.append('RoofMatl')


Data_train['Exterior1st'].astype('category').value_counts()

VinylSd    515
HdBoard    222
MetalSd    220
Wd Sdng    206
Plywood    108
CemntBd     61
BrkFace     50
WdShing     26
Stucco      25
AsbShng     20
BrkComm      2
Stone        2
AsphShn      1
CBlock       1
ImStucc      1
Name: Exterior1st, dtype: int64


Exterior1st = pd.get_dummies(Data_train.Exterior1st,drop_first=True)
Exterior1st = Exterior1st.add_prefix("Exterior1st_")
cat_col_list.append('Exterior1st')


Data_train['Exterior2nd'].astype('category').value_counts()

VinylSd    504
MetalSd    214
HdBoard    207
Wd Sdng    197
Plywood    142
CmentBd     60
Wd Shng     38
Stucco      26
BrkFace     25
AsbShng     20
ImStucc     10
Brk Cmn      7
Stone        5
AsphShn      3
CBlock       1
Other        1
Name: Exterior2nd, dtype: int64


Exterior2nd = pd.get_dummies(Data_train.Exterior2nd,drop_first=True)
Exterior2nd = Exterior2nd.add_prefix("Exterior2nd_")
cat_col_list.append('Exterior2nd')


Data_train['MasVnrType'].astype('category').value_counts()

None       864
BrkFace    445
Stone      128
BrkCmn      15
NO           8
Name: MasVnrType, dtype: int64


MasVnrType = pd.get_dummies(Data_train.MasVnrType,drop_first=True)
MasVnrType = MasVnrType.add_prefix("MasVnrType_")
cat_col_list.append('MasVnrType')


Data_train['ExterQual'].astype('category').value_counts()

TA    906
Gd    488
Ex     52
Fa     14
Name: ExterQual, dtype: int64


ExterQual = pd.get_dummies(Data_train.ExterQual,drop_first=True)
ExterQual = ExterQual.add_prefix("ExterQual_")
cat_col_list.append('ExterQual')


Data_train['ExterCond'].astype('category').value_counts()

TA    1282
Gd     146
Fa      28
Ex       3
Po       1
Name: ExterCond, dtype: int64


# Add to del list
col_del_list.append('ExterCond')


Data_train['Foundation'].astype('category').value_counts()

PConc     647
CBlock    634
BrkTil    146
Slab       24
Stone       6
Wood        3
Name: Foundation, dtype: int64


Foundation = pd.get_dummies(Data_train.Foundation,drop_first=True)
Foundation = Foundation.add_prefix("Foundation_")
cat_col_list.append('Foundation')


Data_train['BsmtQual'].astype('category').value_counts()

TA    649
Gd    618
Ex    121
NO     37
Fa     35
Name: BsmtQual, dtype: int64


BsmtQual = pd.get_dummies(Data_train.BsmtQual,drop_first=True)
BsmtQual = BsmtQual.add_prefix("BsmtQual_")
cat_col_list.append('BsmtQual')


Data_train['BsmtCond'].astype('category').value_counts()

TA    1311
Gd      65
Fa      45
NO      37
Po       2
Name: BsmtCond, dtype: int64


# Add to del list
col_del_list.append('BsmtCond')


Data_train['BsmtExposure'].astype('category').value_counts()

No    953
Av    221
Gd    134
Mn    114
NO     38
Name: BsmtExposure, dtype: int64


BsmtExposure = pd.get_dummies(Data_train.BsmtExposure,drop_first=True)
BsmtExposure = BsmtExposure.add_prefix("BsmtExposure_")
cat_col_list.append('BsmtExposure')


Data_train['BsmtFinType1'].astype('category').value_counts()

Unf    430
GLQ    418
ALQ    220
BLQ    148
Rec    133
LwQ     74
NO      37
Name: BsmtFinType1, dtype: int64


BsmtFinType1 = pd.get_dummies(Data_train.BsmtFinType1,drop_first=True)
BsmtFinType1 = BsmtFinType1.add_prefix("BsmtFinType1_")
cat_col_list.append('BsmtFinType1')


Data_train['BsmtFinType2'].astype('category').value_counts()

Unf    1256
Rec      54
LwQ      46
NO       38
BLQ      33
ALQ      19
GLQ      14
Name: BsmtFinType2, dtype: int64


# Add to del list
col_del_list.append('BsmtFinType2')


Data_train['Heating'].astype('category').value_counts()

GasA     1428
GasW       18
Grav        7
Wall        4
OthW        2
Floor       1
Name: Heating, dtype: int64


# Add to del list
col_del_list.append('Heating')


Data_train['HeatingQC'].astype('category').value_counts()

Ex    741
TA    428
Gd    241
Fa     49
Po      1
Name: HeatingQC, dtype: int64


HeatingQC = pd.get_dummies(Data_train.HeatingQC,drop_first=True)
HeatingQC = HeatingQC.add_prefix("HeatingQC_")
cat_col_list.append('HeatingQC')


Data_train['CentralAir'].astype('category').value_counts()

Y    1365
N      95
Name: CentralAir, dtype: int64


# Add to del list
col_del_list.append('CentralAir')


Data_train['Electrical'].astype('category').value_counts()

SBrkr    1334
FuseA      94
FuseF      27
FuseP       3
Mix         1
NO          1
Name: Electrical, dtype: int64


# Add to del list
col_del_list.append('Electrical')


Data_train['KitchenQual'].astype('category').value_counts()

TA    735
Gd    586
Ex    100
Fa     39
Name: KitchenQual, dtype: int64


KitchenQual = pd.get_dummies(Data_train.KitchenQual,drop_first=True)
KitchenQual = KitchenQual.add_prefix("KitchenQual_")
cat_col_list.append('KitchenQual')


Data_train['Functional'].astype('category').value_counts()

Typ     1360
Min2      34
Min1      31
Mod       15
Maj1      14
Maj2       5
Sev        1
Name: Functional, dtype: int64


# Add to del list
col_del_list.append('Functional')


Data_train['Fireplaces'].astype('category').value_counts()

0    690
1    650
2    115
3      5
Name: Fireplaces, dtype: int64


Data_train['FireplaceQu'].astype('category').value_counts()

NO    690
Gd    380
TA    313
Fa     33
Ex     24
Po     20
Name: FireplaceQu, dtype: int64


FireplaceQu = pd.get_dummies(Data_train.FireplaceQu,drop_first=True)
FireplaceQu = FireplaceQu.add_prefix("FireplaceQu_")
cat_col_list.append('FireplaceQu')


### Handling missing values of FireplaceQU  - missing values are for Fireplaces - 0, replace NA with NO - No Fireplace
#Data_train.FireplaceQu.fillna('NO',inplace=True)
#Data_train['FireplaceQu'].astype('category').value_counts()


Data_train['GarageType'].astype('category').value_counts()

Attchd     870
Detchd     387
BuiltIn     88
NO          81
Basment     19
CarPort      9
2Types       6
Name: GarageType, dtype: int64


GarageType = pd.get_dummies(Data_train.GarageType,drop_first=True)
GarageType = GarageType.add_prefix("GarageType_")
cat_col_list.append('GarageType')


Data_train['GarageFinish'].astype('category').value_counts()

Unf    605
RFn    422
Fin    352
NO      81
Name: GarageFinish, dtype: int64


GarageFinish = pd.get_dummies(Data_train.GarageFinish,drop_first=True)
GarageFinish = GarageFinish.add_prefix("GarageFinish_")
cat_col_list.append('GarageFinish')


Data_train['GarageQual'].astype('category').value_counts()

TA    1311
NO      81
Fa      48
Gd      14
Ex       3
Po       3
Name: GarageQual, dtype: int64


# Add to del list
col_del_list.append('GarageQual')


Data_train['GarageCond'].astype('category').value_counts()

TA    1326
NO      81
Fa      35
Gd       9
Po       7
Ex       2
Name: GarageCond, dtype: int64


# Add to del list
col_del_list.append('GarageCond')


Data_train['PavedDrive'].astype('category').value_counts()

Y    1340
N      90
P      30
Name: PavedDrive, dtype: int64


# Add to del list
col_del_list.append('PavedDrive')


Data_train['SaleType'].astype('category').value_counts()

WD       1267
New       122
COD        43
ConLD       9
ConLI       5
ConLw       5
CWD         4
Oth         3
Con         2
Name: SaleType, dtype: int64


# Add to del list
col_del_list.append('SaleType')


Data_train['SaleCondition'].astype('category').value_counts()

Normal     1198
Partial     125
Abnorml     101
Family       20
Alloca       12
AdjLand       4
Name: SaleCondition, dtype: int64


# Add to del list
col_del_list.append('SaleCondition')


Data_train['KitchenAbvGr'].astype('category').value_counts().plot.bar()

<Axes: >


# Add to del list
col_del_list.append('KitchenAbvGr')


#numeric cat varaibles
OverallQual = pd.get_dummies(Data_train.OverallQual,drop_first=True)
OverallQual = OverallQual.add_prefix("OverallQual_")
cat_col_list.append('OverallQual')


#numeric cat varaibles
OverallCond = pd.get_dummies(Data_train.OverallCond,drop_first=True)
OverallCond = OverallCond.add_prefix("OverallCond_")
cat_col_list.append('OverallCond')


#numeric cat varaibles month
MoSold = pd.get_dummies(Data_train.MoSold,drop_first=True)
MoSold = MoSold.add_prefix("MoSold_")
cat_col_list.append('MoSold')


# delete the feature having 80% or more same values 1460*0.8 = 1168
#col_list_del = ['Street','Utilities','LandContour','LandSlope','Condition1','Condition2','BldgType','RoofMatl','ExterCond','BsmtCond','BsmtFinType2','Heating','CentralAir','Electrical','Functional','GarageQual','GarageCond','PavedDrive','SaleType','SaleCondition','KitchenAbvGr']
Data_train = Data_train.drop(col_del_list, axis = 1)
Data_train.shape

(1460, 46)


Data_train.head()


Data_train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1460 entries, 0 to 1459
Data columns (total 46 columns):
 #   Column        Non-Null Count  Dtype  
---  ------        --------------  -----  
 0   MSSubClass    1460 non-null   int64  
 1   MSZoning      1460 non-null   object 
 2   LotFrontage   1460 non-null   float64
 3   LotArea       1460 non-null   int64  
 4   LotShape      1460 non-null   object 
 5   LotConfig     1460 non-null   object 
 6   Neighborhood  1460 non-null   object 
 7   HouseStyle    1460 non-null   object 
 8   OverallQual   1460 non-null   int64  
 9   OverallCond   1460 non-null   int64  
 10  RoofStyle     1460 non-null   object 
 11  Exterior1st   1460 non-null   object 
 12  Exterior2nd   1460 non-null   object 
 13  MasVnrType    1460 non-null   object 
 14  MasVnrArea    1460 non-null   float64
 15  ExterQual     1460 non-null   object 
 16  Foundation    1460 non-null   object 
 17  BsmtQual      1460 non-null   object 
 18  BsmtExposure  1460 non-null   object 
 19  BsmtFinType1  1460 non-null   object 
 20  BsmtFinSF1    1460 non-null   int64  
 21  BsmtUnfSF     1460 non-null   int64  
 22  TotalBsmtSF   1460 non-null   int64  
 23  HeatingQC     1460 non-null   object 
 24  1stFlrSF      1460 non-null   int64  
 25  2ndFlrSF      1460 non-null   int64  
 26  GrLivArea     1460 non-null   int64  
 27  BsmtFullBath  1460 non-null   int64  
 28  FullBath      1460 non-null   int64  
 29  HalfBath      1460 non-null   int64  
 30  BedroomAbvGr  1460 non-null   int64  
 31  KitchenQual   1460 non-null   object 
 32  TotRmsAbvGrd  1460 non-null   int64  
 33  Fireplaces    1460 non-null   int64  
 34  FireplaceQu   1460 non-null   object 
 35  GarageType    1460 non-null   object 
 36  GarageFinish  1460 non-null   object 
 37  GarageCars    1460 non-null   int64  
 38  GarageArea    1460 non-null   int64  
 39  WoodDeckSF    1460 non-null   int64  
 40  OpenPorchSF   1460 non-null   int64  
 41  MoSold        1460 non-null   int64  
 42  SalePrice     1460 non-null   int64  
 43  age           1460 non-null   int64  
 44  age_Remod     1460 non-null   int64  
 45  age_Garage    1460 non-null   float64
dtypes: float64(3), int64(24), object(19)
memory usage: 524.8+ KB


#Display categorical variables list
cat_col_list

['MSSubClass',
 'MSZoning',
 'LotShape',
 'LotConfig',
 'Neighborhood',
 'HouseStyle',
 'RoofStyle',
 'Exterior1st',
 'Exterior2nd',
 'MasVnrType',
 'ExterQual',
 'Foundation',
 'BsmtQual',
 'BsmtExposure',
 'BsmtFinType1',
 'HeatingQC',
 'KitchenQual',
 'FireplaceQu',
 'GarageType',
 'GarageFinish',
 'OverallQual',
 'OverallCond',
 'MoSold']


#Drop the categorical variables from the Data_train(maintable)
Data_train = Data_train.drop(cat_col_list,axis = 1)

#create table for all dummy variables (categorical variables)
cat_concat = pd.concat([MSSubClass, MSZoning, LotShape, LotConfig, Neighborhood, HouseStyle, RoofStyle, Exterior1st,
 Exterior2nd, MasVnrType, ExterQual, Foundation, BsmtQual, BsmtExposure, BsmtFinType1, HeatingQC, KitchenQual,
 FireplaceQu, GarageType, GarageFinish, OverallQual, OverallCond, MoSold], axis = 1)

#concat dummy variables table to the main table
Data_train = pd.concat([Data_train,cat_concat], axis = 1)


Data_train.shape

(1460, 188)


cor = Data_train.corr()
#plotting correlation heatmap
#plt.figure(figsize=(50,20))
#sns.heatmap(cor, cmap="YlGnBu", annot = True)
#plt.show()
cor


cor["SalePrice"].sort_values(ascending=False)

SalePrice         1.000000
GrLivArea         0.708624
GarageCars        0.640409
GarageArea        0.623431
TotalBsmtSF       0.613581
                    ...   
FireplaceQu_NO   -0.471908
age_Remod        -0.509079
KitchenQual_TA   -0.519298
age              -0.523350
ExterQual_TA     -0.589044
Name: SalePrice, Length: 188, dtype: float64


#import sklearn for splittling 
from sklearn.model_selection import train_test_split


np.random.seed(0)
#Data split into 70:30 ratio of train and test set
df_train, df_test = train_test_split(Data_train, train_size = 0.7, test_size = 0.3, random_state=100 )


from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler()


num_val_col = ['LotFrontage','LotArea','MasVnrArea','BsmtFinSF1','BsmtUnfSF','TotalBsmtSF','1stFlrSF','2ndFlrSF','GrLivArea',
              'BsmtFullBath','FullBath','HalfBath','BedroomAbvGr','TotRmsAbvGrd','Fireplaces','GarageCars','GarageArea',
              'WoodDeckSF','OpenPorchSF','age','age_Remod','age_Garage','SalePrice']


df_train[num_val_col] = scaler.fit_transform(df_train[num_val_col])


df_train.describe()


#divide X and y variables
y_train = df_train.pop('SalePrice')
X_train = df_train


from sklearn.feature_selection import RFE
from sklearn.linear_model import LinearRegression


#Running RFE with the output features = 40
lm = LinearRegression()
lm.fit(X_train,y_train)

rfe = RFE(lm, n_features_to_select = 40)
rfe = rfe.fit(X_train,y_train)


list(zip(X_train.columns, rfe.support_,rfe.ranking_))

[('LotFrontage', True, 1),
 ('LotArea', True, 1),
 ('MasVnrArea', False, 70),
 ('BsmtFinSF1', False, 37),
 ('BsmtUnfSF', False, 130),
 ('TotalBsmtSF', False, 38),
 ('1stFlrSF', True, 1),
 ('2ndFlrSF', True, 1),
 ('GrLivArea', False, 77),
 ('BsmtFullBath', True, 1),
 ('FullBath', False, 15),
 ('HalfBath', False, 92),
 ('BedroomAbvGr', False, 114),
 ('TotRmsAbvGrd', False, 112),
 ('Fireplaces', False, 120),
 ('GarageCars', True, 1),
 ('GarageArea', True, 1),
 ('WoodDeckSF', False, 54),
 ('OpenPorchSF', False, 91),
 ('age', True, 1),
 ('age_Remod', False, 45),
 ('age_Garage', False, 121),
 ('MSSubClass_30', False, 107),
 ('MSSubClass_40', False, 97),
 ('MSSubClass_45', False, 102),
 ('MSSubClass_50', False, 80),
 ('MSSubClass_60', False, 147),
 ('MSSubClass_70', False, 76),
 ('MSSubClass_75', False, 20),
 ('MSSubClass_80', False, 144),
 ('MSSubClass_85', False, 59),
 ('MSSubClass_90', True, 1),
 ('MSSubClass_120', False, 2),
 ('MSSubClass_160', True, 1),
 ('MSSubClass_180', False, 19),
 ('MSSubClass_190', False, 43),
 ('MSZoning_FV', False, 29),
 ('MSZoning_RH', False, 26),
 ('MSZoning_RL', False, 27),
 ('MSZoning_RM', False, 28),
 ('LotShape_IR2', False, 119),
 ('LotShape_IR3', True, 1),
 ('LotShape_Reg', False, 122),
 ('LotConfig_CulDSac', False, 65),
 ('LotConfig_FR2', False, 23),
 ('LotConfig_FR3', False, 79),
 ('LotConfig_Inside', False, 142),
 ('Neighborhood_Blueste', False, 88),
 ('Neighborhood_BrDale', False, 46),
 ('Neighborhood_BrkSide', False, 100),
 ('Neighborhood_ClearCr', False, 47),
 ('Neighborhood_CollgCr', False, 62),
 ('Neighborhood_Crawfor', True, 1),
 ('Neighborhood_Edwards', False, 22),
 ('Neighborhood_Gilbert', False, 61),
 ('Neighborhood_IDOTRR', False, 118),
 ('Neighborhood_MeadowV', False, 104),
 ('Neighborhood_Mitchel', False, 35),
 ('Neighborhood_NAmes', False, 140),
 ('Neighborhood_NPkVill', False, 58),
 ('Neighborhood_NWAmes', False, 141),
 ('Neighborhood_NoRidge', True, 1),
 ('Neighborhood_NridgHt', True, 1),
 ('Neighborhood_OldTown', False, 31),
 ('Neighborhood_SWISU', False, 103),
 ('Neighborhood_Sawyer', False, 136),
 ('Neighborhood_SawyerW', False, 63),
 ('Neighborhood_Somerst', True, 1),
 ('Neighborhood_StoneBr', True, 1),
 ('Neighborhood_Timber', False, 106),
 ('Neighborhood_Veenker', False, 73),
 ('HouseStyle_1.5Unf', False, 48),
 ('HouseStyle_1Story', False, 25),
 ('HouseStyle_2.5Fin', False, 18),
 ('HouseStyle_2.5Unf', False, 16),
 ('HouseStyle_2Story', False, 30),
 ('HouseStyle_SFoyer', False, 60),
 ('HouseStyle_SLvl', False, 82),
 ('RoofStyle_Gable', False, 74),
 ('RoofStyle_Gambrel', False, 24),
 ('RoofStyle_Hip', False, 72),
 ('RoofStyle_Mansard', False, 39),
 ('RoofStyle_Shed', False, 69),
 ('Exterior1st_AsphShn', False, 14),
 ('Exterior1st_BrkComm', False, 89),
 ('Exterior1st_BrkFace', True, 1),
 ('Exterior1st_CBlock', False, 6),
 ('Exterior1st_CemntBd', False, 49),
 ('Exterior1st_HdBoard', False, 71),
 ('Exterior1st_ImStucc', True, 1),
 ('Exterior1st_MetalSd', False, 85),
 ('Exterior1st_Plywood', False, 134),
 ('Exterior1st_Stone', False, 84),
 ('Exterior1st_Stucco', False, 87),
 ('Exterior1st_VinylSd', False, 105),
 ('Exterior1st_Wd Sdng', False, 127),
 ('Exterior1st_WdShing', False, 131),
 ('Exterior2nd_AsphShn', False, 11),
 ('Exterior2nd_Brk Cmn', False, 148),
 ('Exterior2nd_BrkFace', False, 51),
 ('Exterior2nd_CBlock', False, 12),
 ('Exterior2nd_CmentBd', False, 50),
 ('Exterior2nd_HdBoard', False, 75),
 ('Exterior2nd_ImStucc', True, 1),
 ('Exterior2nd_MetalSd', False, 86),
 ('Exterior2nd_Other', False, 17),
 ('Exterior2nd_Plywood', False, 135),
 ('Exterior2nd_Stone', False, 123),
 ('Exterior2nd_Stucco', False, 21),
 ('Exterior2nd_VinylSd', False, 99),
 ('Exterior2nd_Wd Sdng', False, 139),
 ('Exterior2nd_Wd Shng', False, 42),
 ('MasVnrType_BrkFace', False, 66),
 ('MasVnrType_NO', False, 55),
 ('MasVnrType_None', False, 67),
 ('MasVnrType_Stone', False, 68),
 ('ExterQual_Fa', False, 116),
 ('ExterQual_Gd', False, 78),
 ('ExterQual_TA', False, 81),
 ('Foundation_CBlock', False, 101),
 ('Foundation_PConc', False, 111),
 ('Foundation_Slab', False, 145),
 ('Foundation_Stone', False, 41),
 ('Foundation_Wood', False, 57),
 ('BsmtQual_Fa', True, 1),
 ('BsmtQual_Gd', True, 1),
 ('BsmtQual_NO', True, 1),
 ('BsmtQual_TA', True, 1),
 ('BsmtExposure_Gd', True, 1),
 ('BsmtExposure_Mn', False, 108),
 ('BsmtExposure_NO', False, 52),
 ('BsmtExposure_No', False, 56),
 ('BsmtFinType1_BLQ', False, 126),
 ('BsmtFinType1_GLQ', False, 98),
 ('BsmtFinType1_LwQ', False, 64),
 ('BsmtFinType1_NO', True, 1),
 ('BsmtFinType1_Rec', False, 146),
 ('BsmtFinType1_Unf', False, 40),
 ('HeatingQC_Fa', False, 143),
 ('HeatingQC_Gd', False, 124),
 ('HeatingQC_Po', True, 1),
 ('HeatingQC_TA', False, 137),
 ('KitchenQual_Fa', True, 1),
 ('KitchenQual_Gd', True, 1),
 ('KitchenQual_TA', True, 1),
 ('FireplaceQu_Fa', False, 113),
 ('FireplaceQu_Gd', False, 110),
 ('FireplaceQu_NO', False, 83),
 ('FireplaceQu_Po', False, 94),
 ('FireplaceQu_TA', False, 109),
 ('GarageType_Attchd', False, 33),
 ('GarageType_Basment', False, 32),
 ('GarageType_BuiltIn', False, 36),
 ('GarageType_CarPort', False, 44),
 ('GarageType_Detchd', False, 34),
 ('GarageType_NO', False, 10),
 ('GarageFinish_NO', False, 4),
 ('GarageFinish_RFn', False, 96),
 ('GarageFinish_Unf', False, 90),
 ('OverallQual_2', False, 13),
 ('OverallQual_3', False, 8),
 ('OverallQual_4', False, 9),
 ('OverallQual_5', False, 7),
 ('OverallQual_6', False, 5),
 ('OverallQual_7', False, 3),
 ('OverallQual_8', True, 1),
 ('OverallQual_9', True, 1),
 ('OverallQual_10', True, 1),
 ('OverallCond_2', True, 1),
 ('OverallCond_3', True, 1),
 ('OverallCond_4', True, 1),
 ('OverallCond_5', True, 1),
 ('OverallCond_6', True, 1),
 ('OverallCond_7', True, 1),
 ('OverallCond_8', True, 1),
 ('OverallCond_9', True, 1),
 ('MoSold_2', False, 138),
 ('MoSold_3', False, 129),
 ('MoSold_4', False, 132),
 ('MoSold_5', False, 115),
 ('MoSold_6', False, 133),
 ('MoSold_7', False, 95),
 ('MoSold_8', False, 93),
 ('MoSold_9', False, 117),
 ('MoSold_10', False, 53),
 ('MoSold_11', False, 128),
 ('MoSold_12', False, 125)]


#selected list 
col_list = X_train.columns[rfe.support_]
col_list

Index(['LotFrontage', 'LotArea', '1stFlrSF', '2ndFlrSF', 'BsmtFullBath',
       'GarageCars', 'GarageArea', 'age', 'MSSubClass_90', 'MSSubClass_160',
       'LotShape_IR3', 'Neighborhood_Crawfor', 'Neighborhood_NoRidge',
       'Neighborhood_NridgHt', 'Neighborhood_Somerst', 'Neighborhood_StoneBr',
       'Exterior1st_BrkFace', 'Exterior1st_ImStucc', 'Exterior2nd_ImStucc',
       'BsmtQual_Fa', 'BsmtQual_Gd', 'BsmtQual_NO', 'BsmtQual_TA',
       'BsmtExposure_Gd', 'BsmtFinType1_NO', 'HeatingQC_Po', 'KitchenQual_Fa',
       'KitchenQual_Gd', 'KitchenQual_TA', 'OverallQual_8', 'OverallQual_9',
       'OverallQual_10', 'OverallCond_2', 'OverallCond_3', 'OverallCond_4',
       'OverallCond_5', 'OverallCond_6', 'OverallCond_7', 'OverallCond_8',
       'OverallCond_9'],
      dtype='object')


X_train_rfe = X_train[col_list]


import statsmodels.api as sm

#creating model
X_train_rfe = sm.add_constant(X_train_rfe)

#create fitting model
lm = sm.OLS(y_train, X_train_rfe).fit()


print(lm.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:              SalePrice   R-squared:                       0.863
Model:                            OLS   Adj. R-squared:                  0.857
Method:                 Least Squares   F-statistic:                     157.9
Date:                Sun, 22 Oct 2023   Prob (F-statistic):               0.00
Time:                        16:14:10   Log-Likelihood:                 1820.0
No. Observations:                1021   AIC:                            -3560.
Df Residuals:                     981   BIC:                            -3363.
Df Model:                          39                                         
Covariance Type:            nonrobust                                         
========================================================================================
                           coef    std err          t      P>|t|      [0.025      0.975]
----------------------------------------------------------------------------------------
const                    0.1048      0.045      2.331      0.020       0.017       0.193
LotFrontage             -0.0397      0.022     -1.792      0.073      -0.083       0.004
LotArea                  0.1724      0.032      5.398      0.000       0.110       0.235
1stFlrSF                 0.3403      0.022     15.550      0.000       0.297       0.383
2ndFlrSF                 0.1479      0.008     18.826      0.000       0.133       0.163
BsmtFullBath             0.0331      0.008      3.996      0.000       0.017       0.049
GarageCars               0.0896      0.017      5.376      0.000       0.057       0.122
GarageArea              -0.0457      0.021     -2.149      0.032      -0.087      -0.004
age                     -0.1200      0.011    -10.861      0.000      -0.142      -0.098
MSSubClass_90           -0.0350      0.007     -4.691      0.000      -0.050      -0.020
MSSubClass_160          -0.0486      0.008     -6.413      0.000      -0.063      -0.034
LotShape_IR3            -0.0467      0.015     -3.085      0.002      -0.076      -0.017
Neighborhood_Crawfor     0.0488      0.008      6.239      0.000       0.033       0.064
Neighborhood_NoRidge     0.0806      0.009      9.404      0.000       0.064       0.097
Neighborhood_NridgHt     0.0428      0.007      5.983      0.000       0.029       0.057
Neighborhood_Somerst     0.0386      0.007      5.879      0.000       0.026       0.051
Neighborhood_StoneBr     0.0349      0.013      2.770      0.006       0.010       0.060
Exterior1st_BrkFace      0.0351      0.008      4.312      0.000       0.019       0.051
Exterior1st_ImStucc     -0.0748      0.045     -1.654      0.099      -0.164       0.014
Exterior2nd_ImStucc      0.0386      0.016      2.406      0.016       0.007       0.070
BsmtQual_Fa             -0.0395      0.012     -3.308      0.001      -0.063      -0.016
BsmtQual_Gd             -0.0386      0.006     -6.037      0.000      -0.051      -0.026
BsmtQual_NO             -0.0322      0.006     -5.716      0.000      -0.043      -0.021
BsmtQual_TA             -0.0413      0.008     -5.440      0.000      -0.056      -0.026
BsmtExposure_Gd          0.0309      0.005      6.099      0.000       0.021       0.041
BsmtFinType1_NO         -0.0322      0.006     -5.716      0.000      -0.043      -0.021
HeatingQC_Po            -0.0341      0.042     -0.815      0.416      -0.116       0.048
KitchenQual_Fa          -0.0365      0.012     -3.143      0.002      -0.059      -0.014
KitchenQual_Gd          -0.0271      0.007     -3.713      0.000      -0.041      -0.013
KitchenQual_TA          -0.0380      0.008     -4.783      0.000      -0.054      -0.022
OverallQual_8            0.0351      0.005      6.558      0.000       0.025       0.046
OverallQual_9            0.0795      0.011      6.989      0.000       0.057       0.102
OverallQual_10           0.0931      0.015      6.270      0.000       0.064       0.122
OverallCond_2            0.0580      0.050      1.163      0.245      -0.040       0.156
OverallCond_3            0.0329      0.045      0.734      0.463      -0.055       0.121
OverallCond_4            0.0481      0.044      1.088      0.277      -0.039       0.135
OverallCond_5            0.0552      0.044      1.263      0.207      -0.031       0.141
OverallCond_6            0.0730      0.044      1.668      0.096      -0.013       0.159
OverallCond_7            0.0787      0.044      1.801      0.072      -0.007       0.164
OverallCond_8            0.0854      0.044      1.948      0.052      -0.001       0.171
OverallCond_9            0.1198      0.046      2.626      0.009       0.030       0.209
==============================================================================
Omnibus:                      712.444   Durbin-Watson:                   1.961
Prob(Omnibus):                  0.000   Jarque-Bera (JB):            87280.483
Skew:                          -2.304   Prob(JB):                         0.00
Kurtosis:                      48.060   Cond. No.                     1.27e+16
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The smallest eigenvalue is 1.73e-29. This might indicate that there are
strong multicollinearity problems or that the design matrix is singular.


#residual analysis of the training data
#predict the value y_train_pred
y_train_pred = lm.predict(X_train_rfe)


# plot histogram for error term
fig = plt.figure()
sns.distplot((y_train - y_train_pred), bins = 20)
fig.suptitle("Error term" , fontsize = 20)
plt.xlabel("error",fontsize = 10)

Text(0.5, 0, 'error')


from sklearn.metrics import r2_score
r2_score(y_train,y_train_pred)

0.8625557437680991


### Making Prediction


col_list = X_train_rfe.columns
col_list

Index(['const', 'LotFrontage', 'LotArea', '1stFlrSF', '2ndFlrSF',
       'BsmtFullBath', 'GarageCars', 'GarageArea', 'age', 'MSSubClass_90',
       'MSSubClass_160', 'LotShape_IR3', 'Neighborhood_Crawfor',
       'Neighborhood_NoRidge', 'Neighborhood_NridgHt', 'Neighborhood_Somerst',
       'Neighborhood_StoneBr', 'Exterior1st_BrkFace', 'Exterior1st_ImStucc',
       'Exterior2nd_ImStucc', 'BsmtQual_Fa', 'BsmtQual_Gd', 'BsmtQual_NO',
       'BsmtQual_TA', 'BsmtExposure_Gd', 'BsmtFinType1_NO', 'HeatingQC_Po',
       'KitchenQual_Fa', 'KitchenQual_Gd', 'KitchenQual_TA', 'OverallQual_8',
       'OverallQual_9', 'OverallQual_10', 'OverallCond_2', 'OverallCond_3',
       'OverallCond_4', 'OverallCond_5', 'OverallCond_6', 'OverallCond_7',
       'OverallCond_8', 'OverallCond_9'],
      dtype='object')


col_list = ['LotFrontage', 'LotArea', '1stFlrSF', '2ndFlrSF',
       'BsmtFullBath', 'GarageCars', 'GarageArea', 'age', 'MSSubClass_90',
       'MSSubClass_160', 'LotShape_IR3', 'Neighborhood_Crawfor',
       'Neighborhood_NoRidge', 'Neighborhood_NridgHt', 'Neighborhood_Somerst',
       'Neighborhood_StoneBr', 'Exterior1st_BrkFace', 'Exterior1st_ImStucc',
       'Exterior2nd_ImStucc', 'BsmtQual_Fa', 'BsmtQual_Gd', 'BsmtQual_NO',
       'BsmtQual_TA', 'BsmtExposure_Gd', 'BsmtFinType1_NO', 'HeatingQC_Po',
       'KitchenQual_Fa', 'KitchenQual_Gd', 'KitchenQual_TA', 'OverallQual_8',
       'OverallQual_9', 'OverallQual_10', 'OverallCond_2', 'OverallCond_3',
       'OverallCond_4', 'OverallCond_5', 'OverallCond_6', 'OverallCond_7',
       'OverallCond_8', 'OverallCond_9']


#apply scalar for test data for numeric variables
df_test[num_val_col] = scaler.transform(df_test[num_val_col])


#Divide x and y variables
y_test = df_test.pop('SalePrice')


X_test = df_test[col_list]


#add constant 
X_test = sm.add_constant(X_test)

#make prediction 
y_pred = lm.predict(X_test)


#model evaluation
fig = plt.figure()
plt.scatter(y_test,y_pred)
sns.regplot(x=y_test,y=y_pred,ci=None,color = 'blue')

fig.suptitle('y_test vs y_pred', fontsize = 20)

plt.xlabel('y_test',fontsize = 10)
plt.ylabel('y_pred',fontsize = 10)

plt.show()


from sklearn.metrics import r2_score
r2_score(y_test,y_pred)

0.8592142005003942


print("Training Data")
rss = np.sum(np.square(y_train - y_train_pred))
print(rss)
mse = mean_squared_error(y_train,y_train_pred)
print(mse)
rmse = mse**0.5
print(rmse)

Training Data
1.6912554842430993
0.0016564696221773745
0.040699749657428785


print("Testing Data")
rss = np.sum(np.square(y_test - y_pred))
print(rss)
mse = mean_squared_error(y_test,y_pred)
print(mse)
rmse = mse**0.5
print(rmse)

Testing Data
0.765286435658425
0.0017472293051562216
0.0417998720710509


col_x = X_train_rfe.columns

X_train_rfe.pop('const')
X_test.pop('const')

X = X_train_rfe
col_x

Index(['const', 'LotFrontage', 'LotArea', '1stFlrSF', '2ndFlrSF',
       'BsmtFullBath', 'GarageCars', 'GarageArea', 'age', 'MSSubClass_90',
       'MSSubClass_160', 'LotShape_IR3', 'Neighborhood_Crawfor',
       'Neighborhood_NoRidge', 'Neighborhood_NridgHt', 'Neighborhood_Somerst',
       'Neighborhood_StoneBr', 'Exterior1st_BrkFace', 'Exterior1st_ImStucc',
       'Exterior2nd_ImStucc', 'BsmtQual_Fa', 'BsmtQual_Gd', 'BsmtQual_NO',
       'BsmtQual_TA', 'BsmtExposure_Gd', 'BsmtFinType1_NO', 'HeatingQC_Po',
       'KitchenQual_Fa', 'KitchenQual_Gd', 'KitchenQual_TA', 'OverallQual_8',
       'OverallQual_9', 'OverallQual_10', 'OverallCond_2', 'OverallCond_3',
       'OverallCond_4', 'OverallCond_5', 'OverallCond_6', 'OverallCond_7',
       'OverallCond_8', 'OverallCond_9'],
      dtype='object')


X_test.columns

Index(['LotFrontage', 'LotArea', '1stFlrSF', '2ndFlrSF', 'BsmtFullBath',
       'GarageCars', 'GarageArea', 'age', 'MSSubClass_90', 'MSSubClass_160',
       'LotShape_IR3', 'Neighborhood_Crawfor', 'Neighborhood_NoRidge',
       'Neighborhood_NridgHt', 'Neighborhood_Somerst', 'Neighborhood_StoneBr',
       'Exterior1st_BrkFace', 'Exterior1st_ImStucc', 'Exterior2nd_ImStucc',
       'BsmtQual_Fa', 'BsmtQual_Gd', 'BsmtQual_NO', 'BsmtQual_TA',
       'BsmtExposure_Gd', 'BsmtFinType1_NO', 'HeatingQC_Po', 'KitchenQual_Fa',
       'KitchenQual_Gd', 'KitchenQual_TA', 'OverallQual_8', 'OverallQual_9',
       'OverallQual_10', 'OverallCond_2', 'OverallCond_3', 'OverallCond_4',
       'OverallCond_5', 'OverallCond_6', 'OverallCond_7', 'OverallCond_8',
       'OverallCond_9'],
      dtype='object')


feature_names = ['Const','LotFrontage', 'LotArea', '1stFlrSF', '2ndFlrSF',
       'BsmtFullBath', 'GarageCars', 'GarageArea', 'age', 'MSSubClass_90',
       'MSSubClass_160', 'LotShape_IR3', 'Neighborhood_Crawfor',
       'Neighborhood_NoRidge', 'Neighborhood_NridgHt', 'Neighborhood_Somerst',
       'Neighborhood_StoneBr', 'Exterior1st_BrkFace', 'Exterior1st_ImStucc',
       'Exterior2nd_ImStucc', 'BsmtQual_Fa', 'BsmtQual_Gd', 'BsmtQual_NO',
       'BsmtQual_TA', 'BsmtExposure_Gd', 'BsmtFinType1_NO', 'HeatingQC_Po',
       'KitchenQual_Fa', 'KitchenQual_Gd', 'KitchenQual_TA', 'OverallQual_8',
       'OverallQual_9', 'OverallQual_10', 'OverallCond_2', 'OverallCond_3',
       'OverallCond_4', 'OverallCond_5', 'OverallCond_6', 'OverallCond_7',
       'OverallCond_8', 'OverallCond_9']


#Applying Ridge Regression with varying the hyperparameter 'lamda or alpha'

X_seq = np.linspace(X.min(),X.max(),300).reshape(-1,1)
lambdas = [0,0.001,0.1,1,10,100,1000]

for i in lambdas:
    degree = 1 #creating degree 1
    
    ridgecoef = PolynomialFeatures(degree)
    
    X_poly = ridgecoef.fit_transform(X)
    ridgereg = Ridge(alpha = i) 
    
    ridgereg.fit(X_poly, y_train)
    
    y_train_pred = ridgereg.predict(ridgecoef.fit_transform(X))
    print("Lamda:"+str(i))
    print("Training Data:")
    print("r2score: "+str(r2_score(y_train,y_train_pred)))
    print((mean_squared_error(y_train,y_train_pred))**0.5)
    print(ridgereg.coef_)
    
    
    #coefs = pd.DataFrame(ridgereg.coef_, columns=['coefficient importance'],index= feature_names)
    #coefs.plot.barh(figsize=(9,7))
    #plt.title("Ridge Model with regularization,Normalized variables")
    #plt.xlabel("Raw Coefficient Values")
    #plt.axvline(x=0, color=".5")
    #plt.subplots_adjust(left = 0.3)
              
    print("Testing Data:")
    y_test_pred = ridgereg.predict(ridgecoef.transform(X_test))
    print("r2score: "+str(r2_score(y_test,y_test_pred)))
    print((mean_squared_error(y_test,y_test_pred))**0.5)

Lamda:0
Training Data:
r2score: 0.8619396055155792
0.040790872533582725
[ 6.44852470e+12 -3.69143735e-02  1.76369091e-01  3.39225045e-01
  1.46279261e-01  2.91588009e-02  8.80364262e-02 -4.59003217e-02
 -1.20446248e-01 -3.33878022e-02 -4.91875635e-02 -4.27809520e-02
  5.06139052e-02  8.24878251e-02  4.53352515e-02  4.01618481e-02
  3.50785058e-02  3.44124504e-02 -5.92657651e-02  3.59000827e-02
 -3.51860536e-02 -3.62059272e-02 -9.32745221e+12 -3.82330676e-02
  3.20242060e-02  9.32745221e+12 -1.69832407e-02 -4.14153595e-02
 -2.72682939e-02 -3.84479236e-02  3.60291254e-02  7.92398328e-02
  9.54965477e-02  5.43711533e-02  3.05745975e-02  4.32014741e-02
  5.13965021e-02  6.89578287e-02  7.49873500e-02  8.20393002e-02
  1.15162119e-01]
Testing Data:
r2score: 0.8596462137565386
0.04173568955617854
Lamda:0.001
Training Data:
r2score: 0.8625557120840566
0.040699754348539785
[ 0.         -0.03966848  0.17233748  0.34020237  0.14791761  0.03306778
  0.08958112 -0.04565655 -0.11999162 -0.03497005 -0.04855095 -0.0466545
  0.04878863  0.080608    0.04278389  0.03856631  0.03490497  0.03509671
 -0.07473961  0.03855483 -0.03955892 -0.03857712 -0.03220022 -0.04127469
  0.03092726 -0.03220022 -0.03403994 -0.03654699 -0.02706356 -0.03795458
  0.03513227  0.07947635  0.0930768   0.05739029  0.03228381  0.04745174
  0.05462771  0.07239927  0.07809129  0.08481384  0.1192196 ]
Testing Data:
r2score: 0.8592177853257507
0.04179933989310499
Lamda:0.1
Training Data:
r2score: 0.8624333275009848
0.04071787046752303
[ 0.         -0.03567247  0.16432622  0.33196372  0.14662906  0.03290048
  0.08737405 -0.04037823 -0.11864693 -0.03436661 -0.04831056 -0.04499798
  0.04891015  0.08058766  0.04251978  0.0379643   0.03475098  0.03566593
 -0.06661707  0.0369415  -0.04145843 -0.03865476 -0.03239821 -0.04165734
  0.03101843 -0.03239821 -0.03119649 -0.03821795 -0.02727414 -0.03845574
  0.03522291  0.07968144  0.09360243  0.02524068  0.00118712  0.01610647
  0.02339936  0.04102592  0.0467178   0.05314446  0.08678717]
Testing Data:
r2score: 0.8592770504006628
0.04179054083499369
Lamda:1
Training Data:
r2score: 0.859762601553011
0.041111219859311626
[ 0.         -0.01071631  0.11697795  0.27397927  0.13653052  0.03273258
  0.07422855 -0.01004483 -0.11047883 -0.03056786 -0.04669031 -0.03488483
  0.04934448  0.08129877  0.04136794  0.03431765  0.03298502  0.03895924
 -0.03299017  0.02846413 -0.04549205 -0.03883131 -0.03339034 -0.04375461
  0.03373876 -0.03339034 -0.01804672 -0.04347657 -0.02904422 -0.0426561
  0.03613361  0.07979844  0.09517718 -0.00251804 -0.02562573 -0.01230572
 -0.00459928  0.01216628  0.01731552  0.02150638  0.05301748]
Testing Data:
r2score: 0.8551411805427173
0.042400209031549174
Lamda:10
Training Data:
r2score: 0.8295922157550721
0.04531825250695942
[ 0.          0.02503816  0.03775006  0.11803305  0.09830245  0.03048779
  0.06196138  0.04200687 -0.07760294 -0.02051864 -0.03886399 -0.00911499
  0.04216289  0.07584232  0.04088754  0.02217908  0.02097213  0.03586492
 -0.00476943  0.0132867  -0.04144571 -0.03515633 -0.03166916 -0.04571794
  0.04181323 -0.03166916 -0.00432649 -0.04550773 -0.0303654  -0.05422257
  0.04070925  0.06856388  0.07927737 -0.00127463 -0.0211237  -0.0149013
 -0.00454551  0.00713752  0.00914809  0.00672629  0.02815025]
Testing Data:
r2score: 0.8139895651422212
0.04804676821599447
Lamda:100
Training Data:
r2score: 0.6552720272099193
0.06445649752898806
[ 0.00000000e+00  1.37336791e-02  8.31164931e-03  3.01976970e-02
  3.69682988e-02  1.65199815e-02  4.06666736e-02  3.37852043e-02
 -3.13456987e-02 -1.01653214e-02 -1.65421848e-02  4.27582504e-04
  1.41320090e-02  3.37746306e-02  3.13755598e-02  6.17480911e-03
  5.81519056e-03  1.05193282e-02 -7.72285329e-05  3.33307518e-03
 -1.16605277e-02 -1.29050191e-02 -1.45119057e-02 -3.49976375e-02
  3.49243810e-02 -1.45119057e-02 -6.17798059e-04 -1.56524194e-02
 -4.76457296e-03 -4.55625968e-02  3.67557181e-02  3.11260117e-02
  2.86086525e-02  4.38356569e-04 -6.83561152e-03 -8.17878214e-03
  8.65747564e-03  2.42892975e-03  7.46478731e-04 -1.80484138e-03
  6.12596536e-03]
Testing Data:
r2score: 0.6245261613043251
0.068262999631284
Lamda:1000
Training Data:
r2score: 0.2945861856824519
0.09220413975675877
[ 0.00000000e+00  2.50632832e-03  1.23685019e-03  5.18746878e-03
  5.98086935e-03  3.52307897e-03  9.60489579e-03  7.86894738e-03
 -8.54025798e-03 -2.12959555e-03 -2.61633602e-03  2.43599658e-04
  1.78081184e-03  6.16459865e-03  7.81674630e-03  2.03541946e-03
  1.21551077e-03  1.17775311e-03  6.44883113e-05  5.04051308e-04
 -1.62013738e-03  4.36402276e-03 -2.45353175e-03 -1.46897905e-02
  8.55707444e-03 -2.45353175e-03 -9.44000518e-05 -2.24398304e-03
  7.88826523e-03 -1.77744257e-02  1.12039534e-02  5.68406367e-03
  4.55592895e-03  6.87822758e-05 -1.23107072e-03 -2.14750341e-03
  8.58419385e-03 -2.26782043e-03 -2.37630117e-03 -1.14305770e-03
  6.76171683e-04]
Testing Data:
r2score: 0.2761089485623204
0.09478336672986282


#Applying Ridge Regression with varying the hyperparameter 'lamda or alpha'

#X_seq = np.linspace(X.min(),X.max(),300).reshape(-1,1)
lambdas = [0,0.001,0.1,1,10,100,1000]

for i in lambdas:
    degree = 1 #creating degree 1
    
    lassocoef = PolynomialFeatures(degree)
    
    X_poly = lassocoef.fit_transform(X)
    lassoreg = Lasso(alpha = i) 
    
    lassoreg.fit(X_poly, y_train)
    
    y_train_pred = lassoreg.predict(lassocoef.fit_transform(X))
    print("Lamda:"+str(i))
    print("Training Data:")
    print("r2score: "+str(r2_score(y_train,y_train_pred)))
    print((mean_squared_error(y_train,y_train_pred))**0.5)
    print(lassoreg.coef_)
    
    #feature_names = lassoreg[:-1].get_feature_names_out()
    coefs = pd.DataFrame(lassoreg.coef_, columns=['coefficient importance'],index= feature_names)
    
    coefs.plot.barh(figsize=(9,7))
    plt.title("Lasso Model with regularization,Normalized variables")
    plt.xlabel("Raw Coefficient Values")
    plt.axvline(x=0, color=".5")
    plt.subplots_adjust(left = 0.3)
    
              
    print("Testing Data:")
    y_test_pred = lassoreg.predict(lassocoef.transform(X_test))
    print("r2score: "+str(r2_score(y_test,y_test_pred)))
    print((mean_squared_error(y_test,y_test_pred))**0.5)

Lamda:0
Training Data:
r2score: 0.8625543171707977
0.040699960877613454
[ 0.         -0.03972659  0.17246816  0.34028563  0.14793653  0.03304235
  0.08963967 -0.04567394 -0.11999319 -0.03496354 -0.04855494 -0.0466528
  0.04878871  0.08059832  0.04278157  0.03856355  0.03490053  0.03508716
 -0.074852    0.03858957 -0.03972599 -0.03858249 -0.04869784 -0.04128054
  0.03087451 -0.01570742 -0.03408715 -0.03666121 -0.02705376 -0.03793425
  0.03513468  0.07948404  0.09309599  0.05362754  0.02850073  0.04364186
  0.05081577  0.06859487  0.07429948  0.08103838  0.11541116]
Testing Data:
r2score: 0.8592347052680516
0.041796827986071323
Lamda:0.001
Training Data:
r2score: 0.8051467736454287
0.048459869554225314
[ 0.00000000e+00  0.00000000e+00  0.00000000e+00  2.53522277e-01
  1.13365650e-01  1.72547389e-02  8.36301313e-02  0.00000000e+00
 -7.88405959e-02 -1.80007325e-02 -1.65886906e-02 -0.00000000e+00
  2.38126133e-02  5.37312973e-02  3.37254495e-02  3.65546582e-05
  0.00000000e+00  1.06937130e-03 -0.00000000e+00  0.00000000e+00
 -0.00000000e+00 -5.29823070e-03 -1.24152233e-02 -1.00320301e-02
  3.92180539e-02 -1.38784884e-03 -0.00000000e+00 -2.36613911e-03
 -8.23402377e-04 -2.83275466e-02  4.71829180e-02  9.49843730e-02
  9.73908048e-02  0.00000000e+00 -0.00000000e+00 -0.00000000e+00
 -7.93499508e-04  0.00000000e+00  8.05281640e-04  0.00000000e+00
  0.00000000e+00]
Testing Data:
r2score: 0.7958201652667687
0.05033869480512303
Lamda:0.1
Training Data:
r2score: 0.0
0.10978131792054956
[ 0.  0.  0.  0.  0.  0.  0.  0. -0. -0. -0.  0.  0.  0.  0.  0.  0.  0.
  0.  0. -0.  0. -0. -0.  0. -0. -0. -0.  0. -0.  0.  0.  0.  0. -0. -0.
  0. -0. -0. -0.  0.]
Testing Data:
r2score: -0.00030262183303753076
0.11141950647109451
Lamda:1
Training Data:
r2score: 0.0
0.10978131792054956
[ 0.  0.  0.  0.  0.  0.  0.  0. -0. -0. -0.  0.  0.  0.  0.  0.  0.  0.
  0.  0. -0.  0. -0. -0.  0. -0. -0. -0.  0. -0.  0.  0.  0.  0. -0. -0.
  0. -0. -0. -0.  0.]
Testing Data:
r2score: -0.00030262183303753076
0.11141950647109451
Lamda:10
Training Data:
r2score: 0.0
0.10978131792054956
[ 0.  0.  0.  0.  0.  0.  0.  0. -0. -0. -0.  0.  0.  0.  0.  0.  0.  0.
  0.  0. -0.  0. -0. -0.  0. -0. -0. -0.  0. -0.  0.  0.  0.  0. -0. -0.
  0. -0. -0. -0.  0.]
Testing Data:
r2score: -0.00030262183303753076
0.11141950647109451
Lamda:100
Training Data:
r2score: 0.0
0.10978131792054956
[ 0.  0.  0.  0.  0.  0.  0.  0. -0. -0. -0.  0.  0.  0.  0.  0.  0.  0.
  0.  0. -0.  0. -0. -0.  0. -0. -0. -0.  0. -0.  0.  0.  0.  0. -0. -0.
  0. -0. -0. -0.  0.]
Testing Data:
r2score: -0.00030262183303753076
0.11141950647109451
Lamda:1000
Training Data:
r2score: 0.0
0.10978131792054956
[ 0.  0.  0.  0.  0.  0.  0.  0. -0. -0. -0.  0.  0.  0.  0.  0.  0.  0.
  0.  0. -0.  0. -0. -0.  0. -0. -0. -0.  0. -0.  0.  0.  0.  0. -0. -0.
  0. -0. -0. -0.  0.]
Testing Data:
r2score: -0.00030262183303753076
0.11141950647109451


degree = 1 #creating degree 1

#lambda
i = 0.001


#Ridge  

print("RIDGE")
ridgecoef = PolynomialFeatures(degree)
    
X_poly = ridgecoef.fit_transform(X)
ridgereg = Ridge(alpha = i) 
    
ridgereg.fit(X_poly, y_train)
    
y_train_pred = ridgereg.predict(ridgecoef.fit_transform(X))
    
print("Lamda:"+str(i))
print("Training Data:")
print("r2score: "+str(r2_score(y_train,y_train_pred)))
print((mean_squared_error(y_train,y_train_pred))**0.5)
print(ridgereg.coef_)

print("Testing Data:")
y_test_pred = ridgereg.predict(ridgecoef.transform(X_test))
print("r2score: "+str(r2_score(y_test,y_test_pred)))
print((mean_squared_error(y_test,y_test_pred))**0.5)
      
#feature_names = lassoreg[:-1].get_feature_names_out()
coefs = pd.DataFrame(ridgereg.coef_, columns=['coefficient importance'],index= feature_names)

coefs.plot.barh(figsize=(9,7))
plt.title("Ridge Model with regularization,Normalized variables")
plt.xlabel("Raw Coefficient Values")
plt.axvline(x=0, color=".5")
plt.subplots_adjust(left = 0.3)

RIDGE
Lamda:0.001
Training Data:
r2score: 0.8625557120840566
0.040699754348539785
[ 0.         -0.03966848  0.17233748  0.34020237  0.14791761  0.03306778
  0.08958112 -0.04565655 -0.11999162 -0.03497005 -0.04855095 -0.0466545
  0.04878863  0.080608    0.04278389  0.03856631  0.03490497  0.03509671
 -0.07473961  0.03855483 -0.03955892 -0.03857712 -0.03220022 -0.04127469
  0.03092726 -0.03220022 -0.03403994 -0.03654699 -0.02706356 -0.03795458
  0.03513227  0.07947635  0.0930768   0.05739029  0.03228381  0.04745174
  0.05462771  0.07239927  0.07809129  0.08481384  0.1192196 ]
Testing Data:
r2score: 0.8592177853257507
0.04179933989310499


rigde_top_col=['1stFlrSF','LotArea','2ndFlrSF','age','OverallCond_9']


#Lasso

print("LASSO")
lassocoef = PolynomialFeatures(degree)
    
X_poly = lassocoef.fit_transform(X)
lassoreg = Lasso(alpha = i) 
    
lassoreg.fit(X_poly, y_train)
y_train_pred = lassoreg.predict(lassocoef.fit_transform(X))
    
print("Lamda:"+str(i))
print("Training Data:")
print("r2score: "+str(r2_score(y_train,y_train_pred)))
print((mean_squared_error(y_train,y_train_pred))**0.5)
print(lassoreg.coef_)

print("Testing Data:")
y_test_pred = lassoreg.predict(lassocoef.transform(X_test))
print("r2score: "+str(r2_score(y_test,y_test_pred)))
print((mean_squared_error(y_test,y_test_pred))**0.5)

#feature_names = lassoreg[:-1].get_feature_names_out()
coefs = pd.DataFrame(lassoreg.coef_, columns=['coefficient importance'],index= feature_names)

coefs.plot.barh(figsize=(9,7))
plt.title("Lasso Model with regularization,Normalized variables")
plt.xlabel("Raw Coefficient Values")
plt.axvline(x=0, color=".5")
plt.subplots_adjust(left = 0.3)

LASSO
Lamda:0.001
Training Data:
r2score: 0.8051467736454287
0.048459869554225314
[ 0.00000000e+00  0.00000000e+00  0.00000000e+00  2.53522277e-01
  1.13365650e-01  1.72547389e-02  8.36301313e-02  0.00000000e+00
 -7.88405959e-02 -1.80007325e-02 -1.65886906e-02 -0.00000000e+00
  2.38126133e-02  5.37312973e-02  3.37254495e-02  3.65546582e-05
  0.00000000e+00  1.06937130e-03 -0.00000000e+00  0.00000000e+00
 -0.00000000e+00 -5.29823070e-03 -1.24152233e-02 -1.00320301e-02
  3.92180539e-02 -1.38784884e-03 -0.00000000e+00 -2.36613911e-03
 -8.23402377e-04 -2.83275466e-02  4.71829180e-02  9.49843730e-02
  9.73908048e-02  0.00000000e+00 -0.00000000e+00 -0.00000000e+00
 -7.93499508e-04  0.00000000e+00  8.05281640e-04  0.00000000e+00
  0.00000000e+00]
Testing Data:
r2score: 0.7958201652667687
0.05033869480512303


lasso_top_col=['1stFlrSF','2ndFlrSF','age','OverallQual_10','OverallQual_9']


betas = pd.DataFrame(index=feature_names , columns=['Ridge','Lasso'])


betas['Ridge']  = ridgereg.coef_
betas['Lasso']  = lassoreg.coef_

betas


degree = 1 #creating degree 1

#lambda(double of 0.001)
i = 0.002


#Ridge  

print("RIDGE")
ridgecoef = PolynomialFeatures(degree)
    
X_poly = ridgecoef.fit_transform(X)
ridgereg = Ridge(alpha = i) 
    
ridgereg.fit(X_poly, y_train)
    
y_train_pred = ridgereg.predict(ridgecoef.fit_transform(X))
    
print("Lamda:"+str(i))
print("Training Data:")
print("r2score: "+str(r2_score(y_train,y_train_pred)))
print((mean_squared_error(y_train,y_train_pred))**0.5)
print(ridgereg.coef_)

print("Testing Data:")
y_test_pred = ridgereg.predict(ridgecoef.transform(X_test))
print("r2score: "+str(r2_score(y_test,y_test_pred)))
print((mean_squared_error(y_test,y_test_pred))**0.5)
      
#feature_names = lassoreg[:-1].get_feature_names_out()
coefs = pd.DataFrame(ridgereg.coef_, columns=['coefficient importance'],index= feature_names)

coefs.plot.barh(figsize=(9,7))
plt.title("Ridge Model with regularization,Normalized variables")
plt.xlabel("Raw Coefficient Values")
plt.axvline(x=0, color=".5")
plt.subplots_adjust(left = 0.3)

RIDGE
Lamda:0.002
Training Data:
r2score: 0.8625556188986986
0.04069976814547741
[ 0.         -0.03962698  0.17225414  0.34011656  0.14790465  0.03306448
  0.08955932 -0.04559761 -0.11997523 -0.03496315 -0.0485484  -0.04663587
  0.04879004  0.0806069   0.04278049  0.03855931  0.03490373  0.03510248
 -0.07464904  0.03853792 -0.03959073 -0.0385783  -0.0322026  -0.04127926
  0.03092496 -0.0322026  -0.03400937 -0.03657283 -0.02706538 -0.0379591
  0.03513324  0.07947953  0.09308406  0.05678541  0.03169856  0.04686344
  0.0540413   0.07181111  0.07750371  0.08422346  0.11861651]
Testing Data:
r2score: 0.8592212655878217
0.04179882323140653


#Lasso


print("LASSO")
lassocoef = PolynomialFeatures(degree)
    
X_poly = lassocoef.fit_transform(X)
lassoreg = Lasso(alpha = i) 
    
lassoreg.fit(X_poly, y_train)
y_train_pred = lassoreg.predict(lassocoef.fit_transform(X))
    
print("Lamda:"+str(i))
print("Training Data:")
print("r2score: "+str(r2_score(y_train,y_train_pred)))
print((mean_squared_error(y_train,y_train_pred))**0.5)
print(lassoreg.coef_)

print("Testing Data:")
y_test_pred = lassoreg.predict(lassocoef.transform(X_test))
print("r2score: "+str(r2_score(y_test,y_test_pred)))
print((mean_squared_error(y_test,y_test_pred))**0.5)

#feature_names = lassoreg[:-1].get_feature_names_out()
coefs = pd.DataFrame(lassoreg.coef_, columns=['coefficient importance'],index= feature_names)

coefs.plot.barh(figsize=(9,7))
plt.title("Lasso Model with regularization,Normalized variables")
plt.xlabel("Raw Coefficient Values")
plt.axvline(x=0, color=".5")
plt.subplots_adjust(left = 0.3)

LASSO
Lamda:0.002
Training Data:
r2score: 0.7293552227618919
0.05711211790440109
[ 0.          0.          0.          0.14941177  0.07693467  0.
  0.09792412  0.         -0.0485874  -0.         -0.         -0.
  0.          0.0447109   0.03322644  0.          0.          0.
 -0.          0.         -0.         -0.         -0.         -0.01117937
  0.04349696 -0.         -0.         -0.         -0.         -0.03837864
  0.04685108  0.06982025  0.06010389  0.         -0.         -0.
  0.          0.          0.          0.          0.        ]
Testing Data:
r2score: 0.7138636351836265
0.0595911895166149


betas = pd.DataFrame(index=feature_names , columns=['Ridge','Lasso'])


betas['Ridge']  = ridgereg.coef_
betas['Lasso']  = lassoreg.coef_

betas


X = X_train_rfe


degree = 1 #creating degree 1
#lambda
i = 0.001


X_ridge = X.drop(columns = rigde_top_col)
X_ridge_test = X_test.drop(columns = rigde_top_col)


X_ridge.shape

(1021, 35)


X_ridge.columns

Index(['LotFrontage', 'BsmtFullBath', 'GarageCars', 'GarageArea',
       'MSSubClass_90', 'MSSubClass_160', 'LotShape_IR3',
       'Neighborhood_Crawfor', 'Neighborhood_NoRidge', 'Neighborhood_NridgHt',
       'Neighborhood_Somerst', 'Neighborhood_StoneBr', 'Exterior1st_BrkFace',
       'Exterior1st_ImStucc', 'Exterior2nd_ImStucc', 'BsmtQual_Fa',
       'BsmtQual_Gd', 'BsmtQual_NO', 'BsmtQual_TA', 'BsmtExposure_Gd',
       'BsmtFinType1_NO', 'HeatingQC_Po', 'KitchenQual_Fa', 'KitchenQual_Gd',
       'KitchenQual_TA', 'OverallQual_8', 'OverallQual_9', 'OverallQual_10',
       'OverallCond_2', 'OverallCond_3', 'OverallCond_4', 'OverallCond_5',
       'OverallCond_6', 'OverallCond_7', 'OverallCond_8'],
      dtype='object')


feature_names_ridge = ['const','LotFrontage', 'BsmtFullBath', 'GarageCars', 'GarageArea',
       'MSSubClass_90', 'MSSubClass_160', 'LotShape_IR3',
       'Neighborhood_Crawfor', 'Neighborhood_NoRidge', 'Neighborhood_NridgHt',
       'Neighborhood_Somerst', 'Neighborhood_StoneBr', 'Exterior1st_BrkFace',
       'Exterior1st_ImStucc', 'Exterior2nd_ImStucc', 'BsmtQual_Fa',
       'BsmtQual_Gd', 'BsmtQual_NO', 'BsmtQual_TA', 'BsmtExposure_Gd',
       'BsmtFinType1_NO', 'HeatingQC_Po', 'KitchenQual_Fa', 'KitchenQual_Gd',
       'KitchenQual_TA', 'OverallQual_8', 'OverallQual_9', 'OverallQual_10',
       'OverallCond_2', 'OverallCond_3', 'OverallCond_4', 'OverallCond_5',
       'OverallCond_6', 'OverallCond_7', 'OverallCond_8']


#Ridge  

print("RIDGE")
ridgecoef = PolynomialFeatures(degree)
    
X_poly = ridgecoef.fit_transform(X_ridge)
ridgereg = Ridge(alpha = i) 
    
ridgereg.fit(X_poly, y_train)
    
y_train_pred = ridgereg.predict(ridgecoef.fit_transform(X_ridge))
    
print("Lamda:"+str(i))
print("Training Data:")
print("r2score: "+str(r2_score(y_train,y_train_pred)))
print((mean_squared_error(y_train,y_train_pred))**0.5)
print(ridgereg.coef_)

print("Testing Data:")
y_test_pred = ridgereg.predict(ridgecoef.transform(X_ridge_test))
print("r2score: "+str(r2_score(y_test,y_test_pred)))
print((mean_squared_error(y_test,y_test_pred))**0.5)
      
#feature_names = lassoreg[:-1].get_feature_names_out()
coefs = pd.DataFrame(ridgereg.coef_, columns=['coefficient importance'],index= feature_names_ridge)

coefs.plot.barh(figsize=(9,7))
plt.title("Ridge Model with regularization,Normalized variables")
plt.xlabel("Raw Coefficient Values")
plt.axvline(x=0, color=".5")
plt.subplots_adjust(left = 0.3)

RIDGE
Lamda:0.001
Training Data:
r2score: 0.7834556415116392
0.051085997413457165
[ 0.          0.10931535  0.0233091   0.10752951  0.02686144 -0.01137716
 -0.02587471 -0.01330696  0.05519398  0.11899084  0.0307999   0.0257183
  0.02778048  0.04577266 -0.13923112  0.03508675 -0.09586822 -0.04420711
 -0.05051227 -0.07487915  0.03175578 -0.05051227 -0.07534518 -0.07698398
 -0.03718107 -0.06573777  0.04921761  0.1029065   0.16120272 -0.07531687
 -0.0788448  -0.0637915  -0.04554613 -0.03322095 -0.03449167 -0.03751543]
Testing Data:
r2score: 0.7619842188882349
0.05434985670015881


X_lasso = X.drop(columns = lasso_top_col)
X_lasso_test = X_test.drop(columns = lasso_top_col)


X_lasso.columns

Index(['LotFrontage', 'LotArea', 'BsmtFullBath', 'GarageCars', 'GarageArea',
       'MSSubClass_90', 'MSSubClass_160', 'LotShape_IR3',
       'Neighborhood_Crawfor', 'Neighborhood_NoRidge', 'Neighborhood_NridgHt',
       'Neighborhood_Somerst', 'Neighborhood_StoneBr', 'Exterior1st_BrkFace',
       'Exterior1st_ImStucc', 'Exterior2nd_ImStucc', 'BsmtQual_Fa',
       'BsmtQual_Gd', 'BsmtQual_NO', 'BsmtQual_TA', 'BsmtExposure_Gd',
       'BsmtFinType1_NO', 'HeatingQC_Po', 'KitchenQual_Fa', 'KitchenQual_Gd',
       'KitchenQual_TA', 'OverallQual_8', 'OverallCond_2', 'OverallCond_3',
       'OverallCond_4', 'OverallCond_5', 'OverallCond_6', 'OverallCond_7',
       'OverallCond_8', 'OverallCond_9'],
      dtype='object')


feature_names_lasso = ['const','LotFrontage', 'LotArea', 'BsmtFullBath', 'GarageCars', 'GarageArea',
       'MSSubClass_90', 'MSSubClass_160', 'LotShape_IR3',
       'Neighborhood_Crawfor', 'Neighborhood_NoRidge', 'Neighborhood_NridgHt',
       'Neighborhood_Somerst', 'Neighborhood_StoneBr', 'Exterior1st_BrkFace',
       'Exterior1st_ImStucc', 'Exterior2nd_ImStucc', 'BsmtQual_Fa',
       'BsmtQual_Gd', 'BsmtQual_NO', 'BsmtQual_TA', 'BsmtExposure_Gd',
       'BsmtFinType1_NO', 'HeatingQC_Po', 'KitchenQual_Fa', 'KitchenQual_Gd',
       'KitchenQual_TA', 'OverallQual_8', 'OverallCond_2', 'OverallCond_3',
       'OverallCond_4', 'OverallCond_5', 'OverallCond_6', 'OverallCond_7',
       'OverallCond_8', 'OverallCond_9']


X_lasso.shape

(1021, 35)


#Lasso

print("LASSO")
lassocoef = PolynomialFeatures(degree)
    
X_poly = lassocoef.fit_transform(X_lasso)
lassoreg = Lasso(alpha = i) 
    
lassoreg.fit(X_poly, y_train)
y_train_pred = lassoreg.predict(lassocoef.fit_transform(X_lasso))
    
print("Lamda:"+str(i))
print("Training Data:")
print("r2score: "+str(r2_score(y_train,y_train_pred)))
print((mean_squared_error(y_train,y_train_pred))**0.5)
print(lassoreg.coef_)

print("Testing Data:")
y_test_pred = lassoreg.predict(lassocoef.transform(X_lasso_test))
print("r2score: "+str(r2_score(y_test,y_test_pred)))
print((mean_squared_error(y_test,y_test_pred))**0.5)

#feature_names = lassoreg[:-1].get_feature_names_out()
coefs = pd.DataFrame(lassoreg.coef_, columns=['coefficient importance'],index= feature_names_lasso )

coefs.plot.barh(figsize=(9,7))
plt.title("Lasso Model with regularization,Normalized variables")
plt.xlabel("Raw Coefficient Values")
plt.axvline(x=0, color=".5")
plt.subplots_adjust(left = 0.3)

LASSO
Lamda:0.001
Training Data:
r2score: 0.7047142382911329
0.05965539055961897
[ 0.          0.          0.          0.0024356   0.11020291  0.05692849
 -0.         -0.01258588  0.          0.02792744  0.10989839  0.04419875
  0.          0.          0.00299286 -0.          0.         -0.03937701
 -0.03040612 -0.04516775 -0.05340777  0.05191409 -0.01408318 -0.
 -0.07265162 -0.0528089  -0.09570708  0.03388125 -0.         -0.
 -0.          0.          0.          0.         -0.          0.        ]
Testing Data:
r2score: 0.668442642034726
0.06414678017773935


betas = pd.DataFrame(index=feature_names_lasso , columns=['Lasso'])

betas['Lasso']  = lassoreg.coef_

betas

	Id	MSSubClass	LotFrontage	LotArea	OverallQual	OverallCond	YearBuilt	YearRemodAdd	MasVnrArea	BsmtFinSF1	...	WoodDeckSF	OpenPorchSF	EnclosedPorch	3SsnPorch	ScreenPorch	PoolArea	MiscVal	MoSold	YrSold	SalePrice
Id	1.000000	0.011156	-0.010601	-0.033226	-0.028365	0.012609	-0.012713	-0.021998	-0.050298	-0.005024	...	-0.029643	-0.000477	0.002889	-0.046635	0.001330	0.057044	-0.006242	0.021172	0.000712	-0.021917
MSSubClass	0.011156	1.000000	-0.386347	-0.139781	0.032628	-0.059316	0.027850	0.040581	0.022936	-0.069836	...	-0.012579	-0.006100	-0.012037	-0.043825	-0.026030	0.008283	-0.007683	-0.013585	-0.021407	-0.084284
LotFrontage	-0.010601	-0.386347	1.000000	0.426095	0.251646	-0.059213	0.123349	0.088866	0.193458	0.233633	...	0.088521	0.151972	0.010700	0.070029	0.041383	0.206167	0.003368	0.011200	0.007450	0.351799
LotArea	-0.033226	-0.139781	0.426095	1.000000	0.105806	-0.005636	0.014228	0.013788	0.104160	0.214103	...	0.171698	0.084774	-0.018340	0.020423	0.043160	0.077672	0.038068	0.001205	-0.014261	0.263843
OverallQual	-0.028365	0.032628	0.251646	0.105806	1.000000	-0.091932	0.572323	0.550684	0.411876	0.239666	...	0.238923	0.308819	-0.113937	0.030371	0.064886	0.065166	-0.031406	0.070815	-0.027347	0.790982
OverallCond	0.012609	-0.059316	-0.059213	-0.005636	-0.091932	1.000000	-0.375983	0.073741	-0.128101	-0.046231	...	-0.003334	-0.032589	0.070356	0.025504	0.054811	-0.001985	0.068777	-0.003511	0.043950	-0.077856
YearBuilt	-0.012713	0.027850	0.123349	0.014228	0.572323	-0.375983	1.000000	0.592855	0.315707	0.249503	...	0.224880	0.188686	-0.387268	0.031355	-0.050364	0.004950	-0.034383	0.012398	-0.013618	0.522897
YearRemodAdd	-0.021998	0.040581	0.088866	0.013788	0.550684	0.073741	0.592855	1.000000	0.179618	0.128451	...	0.205726	0.226298	-0.193919	0.045286	-0.038740	0.005829	-0.010286	0.021490	0.035743	0.507101
MasVnrArea	-0.050298	0.022936	0.193458	0.104160	0.411876	-0.128101	0.315707	0.179618	1.000000	0.264736	...	0.159718	0.125703	-0.110204	0.018796	0.061466	0.011723	-0.029815	-0.005965	-0.008201	0.477493
BsmtFinSF1	-0.005024	-0.069836	0.233633	0.214103	0.239666	-0.046231	0.249503	0.128451	0.264736	1.000000	...	0.204306	0.111761	-0.102303	0.026451	0.062021	0.140491	0.003571	-0.015727	0.014359	0.386420
BsmtFinSF2	-0.005968	-0.065649	0.049900	0.111170	-0.059119	0.040229	-0.049107	-0.067759	-0.072319	-0.050117	...	0.067898	0.003093	0.036543	-0.029993	0.088871	0.041709	0.004940	-0.015211	0.031706	-0.011378
BsmtUnfSF	-0.007940	-0.140759	0.132644	-0.002618	0.308159	-0.136841	0.149040	0.181133	0.114442	-0.495251	...	-0.005316	0.129005	-0.002538	0.020764	-0.012579	-0.035092	-0.023837	0.034888	-0.041258	0.214479
TotalBsmtSF	-0.015415	-0.238518	0.392075	0.260833	0.537808	-0.171098	0.391452	0.291066	0.363936	0.522396	...	0.232019	0.247264	-0.095478	0.037384	0.084489	0.126053	-0.018479	0.013196	-0.014969	0.613581
1stFlrSF	0.010496	-0.251758	0.457181	0.299475	0.476224	-0.144203	0.281986	0.240379	0.344501	0.445863	...	0.235459	0.211671	-0.065292	0.056104	0.088758	0.131525	-0.021096	0.031372	-0.013604	0.605852
2ndFlrSF	0.005590	0.307886	0.080177	0.050986	0.295493	0.028942	0.010308	0.140024	0.174561	-0.137079	...	0.092165	0.208026	0.061989	-0.024358	0.040606	0.081487	0.016197	0.035164	-0.028700	0.319334
LowQualFinSF	-0.044230	0.046474	0.038469	0.004779	-0.030429	0.025494	-0.183784	-0.062419	-0.069071	-0.064503	...	-0.025444	0.018251	0.061081	-0.004296	0.026799	0.062157	-0.003793	-0.022174	-0.028921	-0.025606
GrLivArea	0.008273	0.074853	0.402797	0.263116	0.593007	-0.079686	0.199010	0.287389	0.390857	0.208171	...	0.247433	0.330224	0.009113	0.020643	0.101510	0.170205	-0.002416	0.050240	-0.036526	0.708624
BsmtFullBath	0.002289	0.003491	0.100949	0.158155	0.111098	-0.054942	0.187599	0.119470	0.085310	0.649212	...	0.175315	0.067341	-0.049911	-0.000106	0.023148	0.067616	-0.023047	-0.025361	0.067049	0.227122
BsmtHalfBath	-0.020155	-0.002333	-0.007234	0.048046	-0.040150	0.117821	-0.038162	-0.012337	0.026673	0.067418	...	0.040161	-0.025324	-0.008555	0.035114	0.032121	0.020025	-0.007367	0.032873	-0.046524	-0.016844
FullBath	0.005587	0.131608	0.198769	0.126031	0.550600	-0.194149	0.468271	0.439046	0.276833	0.058543	...	0.187703	0.259977	-0.115093	0.035353	-0.008106	0.049604	-0.014290	0.055872	-0.019669	0.560664
HalfBath	0.006784	0.177354	0.053532	0.014259	0.273458	-0.060769	0.242656	0.183331	0.201444	0.004262	...	0.108080	0.199740	-0.095317	-0.004972	0.072426	0.022381	0.001290	-0.009050	-0.010269	0.284108
BedroomAbvGr	0.037719	-0.023438	0.263170	0.119690	0.101676	0.012980	-0.070651	-0.040581	0.102821	-0.107355	...	0.046854	0.093810	0.041570	-0.024478	0.044300	0.070703	0.007767	0.046544	-0.036014	0.168213
KitchenAbvGr	0.002951	0.281721	-0.006069	-0.017784	-0.183882	-0.087001	-0.174800	-0.149598	-0.037610	-0.081007	...	-0.090130	-0.070091	0.037312	-0.024600	-0.051613	-0.014525	0.062341	0.026589	0.031687	-0.135907
TotRmsAbvGrd	0.027239	0.040380	0.352096	0.190015	0.427452	-0.057583	0.095589	0.191740	0.280682	0.044316	...	0.165984	0.234192	0.004151	-0.006683	0.059383	0.083757	0.024763	0.036907	-0.034516	0.533723
Fireplaces	-0.019772	-0.045569	0.266639	0.271364	0.396765	-0.023820	0.147716	0.112581	0.249070	0.260011	...	0.200019	0.169405	-0.024822	0.011257	0.184530	0.095074	0.001409	0.046357	-0.024096	0.466929
GarageYrBlt	0.000072	0.085072	0.070250	-0.024947	0.547766	-0.324297	0.825667	0.642277	0.252691	0.153484	...	0.224577	0.228425	-0.297003	0.023544	-0.075418	-0.014501	-0.032417	0.005337	-0.001014	0.486362
GarageCars	0.016570	-0.040110	0.285691	0.154871	0.600671	-0.185758	0.537850	0.420622	0.364204	0.224054	...	0.226342	0.213569	-0.151434	0.035765	0.050494	0.020934	-0.043080	0.040522	-0.039117	0.640409
GarageArea	0.017634	-0.098672	0.344997	0.180403	0.562022	-0.151521	0.478954	0.371600	0.373066	0.296970	...	0.224666	0.241435	-0.121777	0.035087	0.051412	0.061047	-0.027400	0.027974	-0.027378	0.623431
WoodDeckSF	-0.029643	-0.012579	0.088521	0.171698	0.238923	-0.003334	0.224880	0.205726	0.159718	0.204306	...	1.000000	0.058661	-0.125989	-0.032771	-0.074181	0.073378	-0.009551	0.021011	0.022270	0.324413
OpenPorchSF	-0.000477	-0.006100	0.151972	0.084774	0.308819	-0.032589	0.188686	0.226298	0.125703	0.111761	...	0.058661	1.000000	-0.093079	-0.005842	0.074304	0.060762	-0.018584	0.071255	-0.057619	0.315856
EnclosedPorch	0.002889	-0.012037	0.010700	-0.018340	-0.113937	0.070356	-0.387268	-0.193919	-0.110204	-0.102303	...	-0.125989	-0.093079	1.000000	-0.037305	-0.082864	0.054203	0.018361	-0.028887	-0.009916	-0.128578
3SsnPorch	-0.046635	-0.043825	0.070029	0.020423	0.030371	0.025504	0.031355	0.045286	0.018796	0.026451	...	-0.032771	-0.005842	-0.037305	1.000000	-0.031436	-0.007992	0.000354	0.029474	0.018645	0.044584
ScreenPorch	0.001330	-0.026030	0.041383	0.043160	0.064886	0.054811	-0.050364	-0.038740	0.061466	0.062021	...	-0.074181	0.074304	-0.082864	-0.031436	1.000000	0.051307	0.031946	0.023217	0.010694	0.111447
PoolArea	0.057044	0.008283	0.206167	0.077672	0.065166	-0.001985	0.004950	0.005829	0.011723	0.140491	...	0.073378	0.060762	0.054203	-0.007992	0.051307	1.000000	0.029669	-0.033737	-0.059689	0.092404
MiscVal	-0.006242	-0.007683	0.003368	0.038068	-0.031406	0.068777	-0.034383	-0.010286	-0.029815	0.003571	...	-0.009551	-0.018584	0.018361	0.000354	0.031946	0.029669	1.000000	-0.006495	0.004906	-0.021190
MoSold	0.021172	-0.013585	0.011200	0.001205	0.070815	-0.003511	0.012398	0.021490	-0.005965	-0.015727	...	0.021011	0.071255	-0.028887	0.029474	0.023217	-0.033737	-0.006495	1.000000	-0.145721	0.046432
YrSold	0.000712	-0.021407	0.007450	-0.014261	-0.027347	0.043950	-0.013618	0.035743	-0.008201	0.014359	...	0.022270	-0.057619	-0.009916	0.018645	0.010694	-0.059689	0.004906	-0.145721	1.000000	-0.028923
SalePrice	-0.021917	-0.084284	0.351799	0.263843	0.790982	-0.077856	0.522897	0.507101	0.477493	0.386420	...	0.324413	0.315856	-0.128578	0.044584	0.111447	0.092404	-0.021190	0.046432	-0.028923	1.000000

	LotFrontage	LotArea	MasVnrArea	BsmtFinSF1	BsmtUnfSF	TotalBsmtSF	1stFlrSF	2ndFlrSF	GrLivArea	BsmtFullBath	...	MoSold_3	MoSold_4	MoSold_5	MoSold_6	MoSold_7	MoSold_8	MoSold_9	MoSold_10	MoSold_11	MoSold_12
LotFrontage	1.000000	0.304522	0.178469	0.214367	0.124098	0.363472	0.413773	0.072388	0.368007	0.090343	...	0.015397	-0.068741	-0.008092	0.003820	0.014998	-0.036235	0.042033	-0.027674	0.060188	-0.010418
LotArea	0.304522	1.000000	0.103321	0.214103	-0.002618	0.260833	0.299475	0.050986	0.263116	0.158155	...	0.002208	-0.032536	-0.042141	0.064209	-0.018250	0.019117	0.004245	-0.032004	0.016914	-0.001071
MasVnrArea	0.178469	0.103321	1.000000	0.261256	0.113862	0.360067	0.339850	0.173800	0.388052	0.083010	...	0.033699	-0.043721	-0.053327	0.024093	-0.002133	0.009243	-0.002265	0.004953	0.013301	-0.010876
BsmtFinSF1	0.214367	0.214103	0.261256	1.000000	-0.495251	0.522396	0.445863	-0.137079	0.208171	0.649212	...	0.008234	0.003818	-0.020406	-0.024166	-0.035538	-0.009820	0.006186	0.012646	0.045063	-0.009999
BsmtUnfSF	0.124098	-0.002618	0.113862	-0.495251	1.000000	0.415360	0.317987	0.004469	0.240257	-0.422900	...	0.017249	-0.023770	-0.028910	-0.021212	0.016779	0.016158	0.022900	0.016096	-0.004482	0.026173
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
MoSold_8	-0.036235	0.019117	0.009243	-0.009820	0.016158	0.004755	0.010161	0.023561	0.026972	0.010059	...	-0.084488	-0.098728	-0.121695	-0.138248	-0.131921	1.000000	-0.064124	-0.076936	-0.072222	-0.061967
MoSold_9	0.042033	0.004245	-0.002265	0.006186	0.022900	0.026563	0.027410	0.030732	0.050365	-0.031169	...	-0.059418	-0.069432	-0.085584	-0.097225	-0.092776	-0.064124	1.000000	-0.054106	-0.050791	-0.043579
MoSold_10	-0.027674	-0.032004	0.004953	0.012646	0.016096	0.027637	0.038300	-0.045281	-0.009479	-0.004721	...	-0.071289	-0.083304	-0.102683	-0.116650	-0.111311	-0.076936	-0.054106	1.000000	-0.060939	-0.052286
MoSold_11	0.060188	0.016914	0.013301	0.045063	-0.004482	0.042519	0.045191	0.018278	0.045770	0.043177	...	-0.066921	-0.078199	-0.096391	-0.109502	-0.104491	-0.072222	-0.050791	-0.060939	1.000000	-0.049082
MoSold_12	-0.010418	-0.001071	-0.010876	-0.009999	0.026173	0.005557	0.007704	-0.006716	-0.000837	-0.020754	...	-0.057418	-0.067096	-0.082704	-0.093954	-0.089654	-0.061967	-0.043579	-0.052286	-0.049082	1.000000

	Id	MSSubClass	MSZoning	LotFrontage	LotArea	Street	Alley	LotShape	LandContour	Utilities	...	PoolQC	Fence	MiscFeature	MoSold	YrSold	SaleType	SaleCondition	SalePrice
0	1	60	RL	65.0	8450	Pave	NaN	Reg	Lvl	AllPub	...	NaN	NaN	NaN	2	2008	WD	Normal	208500
1	2	20	RL	80.0	9600	Pave	NaN	Reg	Lvl	AllPub	...	NaN	NaN	NaN	5	2007	WD	Normal	181500
2	3	60	RL	68.0	11250	Pave	NaN	IR1	Lvl	AllPub	...	NaN	NaN	NaN	9	2008	WD	Normal	223500
3	4	70	RL	60.0	9550	Pave	NaN	IR1	Lvl	AllPub	...	NaN	NaN	NaN	2	2006	WD	Abnorml	140000
4	5	60	RL	84.0	14260	Pave	NaN	IR1	Lvl	AllPub	...	NaN	NaN	NaN	12	2008	WD	Normal	250000

	Id	MSSubClass	LotFrontage	LotArea	OverallQual	OverallCond	YearBuilt	YearRemodAdd	MasVnrArea	BsmtFinSF1	...	WoodDeckSF	OpenPorchSF	EnclosedPorch	3SsnPorch	ScreenPorch	PoolArea	MiscVal	MoSold	YrSold	SalePrice
count	1460.000000	1460.000000	1201.000000	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000	1452.000000	1460.000000	...	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000
mean	730.500000	56.897260	70.049958	10516.828082	6.099315	5.575342	1971.267808	1984.865753	103.685262	443.639726	...	94.244521	46.660274	21.954110	3.409589	15.060959	2.758904	43.489041	6.321918	2007.815753	180921.195890
std	421.610009	42.300571	24.284752	9981.264932	1.382997	1.112799	30.202904	20.645407	181.066207	456.098091	...	125.338794	66.256028	61.119149	29.317331	55.757415	40.177307	496.123024	2.703626	1.328095	79442.502883
min	1.000000	20.000000	21.000000	1300.000000	1.000000	1.000000	1872.000000	1950.000000	0.000000	0.000000	...	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	1.000000	2006.000000	34900.000000
25%	365.750000	20.000000	59.000000	7553.500000	5.000000	5.000000	1954.000000	1967.000000	0.000000	0.000000	...	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	5.000000	2007.000000	129975.000000
50%	730.500000	50.000000	69.000000	9478.500000	6.000000	5.000000	1973.000000	1994.000000	0.000000	383.500000	...	0.000000	25.000000	0.000000	0.000000	0.000000	0.000000	0.000000	6.000000	2008.000000	163000.000000
75%	1095.250000	70.000000	80.000000	11601.500000	7.000000	6.000000	2000.000000	2004.000000	166.000000	712.250000	...	168.000000	68.000000	0.000000	0.000000	0.000000	0.000000	0.000000	8.000000	2009.000000	214000.000000
max	1460.000000	190.000000	313.000000	215245.000000	10.000000	9.000000	2010.000000	2010.000000	1600.000000	5644.000000	...	857.000000	547.000000	552.000000	508.000000	480.000000	738.000000	15500.000000	12.000000	2010.000000	755000.000000

	MSSubClass_30	MSSubClass_40	MSSubClass_45	MSSubClass_50	MSSubClass_60	MSSubClass_70	MSSubClass_75	MSSubClass_80	MSSubClass_85	MSSubClass_90	MSSubClass_120	MSSubClass_160	MSSubClass_180	MSSubClass_190
0	0	0	0	0	1	0	0	0	0	0	0	0	0	0
1	0	0	0	0	0	0	0	0	0	0	0	0	0	0
2	0	0	0	0	1	0	0	0	0	0	0	0	0	0
3	0	0	0	0	0	1	0	0	0	0	0	0	0	0
4	0	0	0	0	1	0	0	0	0	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1455	0	0	0	0	1	0	0	0	0	0	0	0	0	0
1456	0	0	0	0	0	0	0	0	0	0	0	0	0	0
1457	0	0	0	0	0	1	0	0	0	0	0	0	0	0
1458	0	0	0	0	0	0	0	0	0	0	0	0	0	0
1459	0	0	0	0	0	0	0	0	0	0	0	0	0	0

	MSSubClass	MSZoning	LotFrontage	LotArea	LotShape	LotConfig	Neighborhood	HouseStyle	OverallQual	OverallCond	...	GarageFinish	GarageCars	GarageArea	WoodDeckSF	OpenPorchSF	MoSold	SalePrice	age	age_Remod	age_Garage
0	60	RL	65.0	8450	Reg	Inside	CollgCr	2Story	7	5	...	RFn	2	548	0	61	2	208500	5	5	5.0
1	20	RL	80.0	9600	Reg	FR2	Veenker	1Story	6	8	...	RFn	2	460	298	0	5	181500	31	31	31.0
2	60	RL	68.0	11250	IR1	Inside	CollgCr	2Story	7	5	...	RFn	2	608	0	42	9	223500	7	6	7.0
3	70	RL	60.0	9550	IR1	Corner	Crawfor	2Story	7	5	...	Unf	3	642	0	35	2	140000	91	36	8.0
4	60	RL	84.0	14260	IR1	FR2	NoRidge	2Story	8	5	...	RFn	3	836	192	84	12	250000	8	8	8.0

	LotFrontage	LotArea	MasVnrArea	BsmtFinSF1	BsmtUnfSF	TotalBsmtSF	1stFlrSF	2ndFlrSF	GrLivArea	BsmtFullBath	...	MoSold_3	MoSold_4	MoSold_5	MoSold_6	MoSold_7	MoSold_8	MoSold_9	MoSold_10	MoSold_11	MoSold_12
count	1021.000000	1021.000000	1021.000000	1021.000000	1021.000000	1021.000000	1021.000000	1021.000000	1021.000000	1021.000000	...	1021.000000	1021.000000	1021.000000	1021.000000	1021.000000	1021.000000	1021.000000	1021.000000	1021.000000	1021.000000
mean	0.166249	0.042143	0.065306	0.079337	0.241388	0.173773	0.184341	0.165943	0.207345	0.146588	...	0.070519	0.110676	0.142997	0.169442	0.147894	0.078355	0.041136	0.061704	0.057786	0.042116
std	0.075615	0.048226	0.117088	0.082377	0.192066	0.075145	0.092132	0.210799	0.102232	0.175127	...	0.256145	0.313884	0.350241	0.375325	0.355169	0.268860	0.198702	0.240735	0.233454	0.200951
min	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	...	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	0.133562	0.027923	0.000000	0.000000	0.092466	0.129787	0.116435	0.000000	0.133743	0.000000	...	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
50%	0.164384	0.037531	0.000000	0.069454	0.197774	0.162357	0.165278	0.000000	0.197540	0.000000	...	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
75%	0.195205	0.046943	0.098750	0.126152	0.345034	0.215057	0.243056	0.352058	0.255573	0.333333	...	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
max	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	...	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000

	Ridge	Lasso
Const	0.000000	0.000000
LotFrontage	-0.039668	0.000000
LotArea	0.172337	0.000000
1stFlrSF	0.340202	0.253522
2ndFlrSF	0.147918	0.113366
BsmtFullBath	0.033068	0.017255
GarageCars	0.089581	0.083630
GarageArea	-0.045657	0.000000
age	-0.119992	-0.078841
MSSubClass_90	-0.034970	-0.018001
MSSubClass_160	-0.048551	-0.016589
LotShape_IR3	-0.046654	-0.000000
Neighborhood_Crawfor	0.048789	0.023813
Neighborhood_NoRidge	0.080608	0.053731
Neighborhood_NridgHt	0.042784	0.033725
Neighborhood_Somerst	0.038566	0.000037
Neighborhood_StoneBr	0.034905	0.000000
Exterior1st_BrkFace	0.035097	0.001069
Exterior1st_ImStucc	-0.074740	-0.000000
Exterior2nd_ImStucc	0.038555	0.000000
BsmtQual_Fa	-0.039559	-0.000000
BsmtQual_Gd	-0.038577	-0.005298
BsmtQual_NO	-0.032200	-0.012415
BsmtQual_TA	-0.041275	-0.010032
BsmtExposure_Gd	0.030927	0.039218
BsmtFinType1_NO	-0.032200	-0.001388
HeatingQC_Po	-0.034040	-0.000000
KitchenQual_Fa	-0.036547	-0.002366
KitchenQual_Gd	-0.027064	-0.000823
KitchenQual_TA	-0.037955	-0.028328
OverallQual_8	0.035132	0.047183
OverallQual_9	0.079476	0.094984
OverallQual_10	0.093077	0.097391
OverallCond_2	0.057390	0.000000
OverallCond_3	0.032284	-0.000000
OverallCond_4	0.047452	-0.000000
OverallCond_5	0.054628	-0.000793
OverallCond_6	0.072399	0.000000
OverallCond_7	0.078091	0.000805
OverallCond_8	0.084814	0.000000
OverallCond_9	0.119220	0.000000

Assignment - Advanced Regression¶

Problem Statement:¶

Business Goal:¶

Steps:¶

Step 1:Import libraries, Data¶

Data Understanding and Exploration¶

Insight:¶

Data description:¶

Step 2: Perform EDA - Data cleanup, Preparation, Dummy variables etc¶

Insights:¶

Data Preparation & Analysis¶

1. Using Missingno library identify the missing values more than 80%¶

Insights:¶

2. Check and Removing the columns with only one value or having majorly(more than 80%) one value¶

Insights:¶

Insight¶

Insight:¶

Categorical Variable - Year¶

3. Handling remaining Missing values¶

Categorical Variable¶

Insight :¶

Insight:¶

Insight - Handle missing values of FireplaceQC¶

Insight:¶

Insights:¶

Step 3: Reduce the features using RFE¶

Split Train and Test Data¶

Model preparation¶

RFE - Recursive Feature Eliminanation¶

Insight¶

Step 4: Ridge Regression model¶

Insight :¶

Step 5: Lasso Regression model¶

Insight:¶

Insights: RIDGE¶

Insights: LASSO¶

Build Ridge and Lasso models by removing there Top 5 features respectivly¶

Insights:¶

Insights:¶

Ridge Regression Model:¶

Lasso Regression Model:¶